Add asyncio support for LLM (OpenAI), Chain (LLMChain, LLMMathChain), and Agent (#841)

Supporting asyncio in langchain primitives allows for users to run them
concurrently and creates more seamless integration with
asyncio-supported frameworks (FastAPI, etc.)

Summary of changes:

**LLM**
* Add `agenerate` and `_agenerate`
* Implement in OpenAI by leveraging `client.Completions.acreate`

**Chain**
* Add `arun`, `acall`, `_acall`
* Implement them in `LLMChain` and `LLMMathChain` for now

**Agent**
* Refactor and leverage async chain and llm methods
* Add ability for `Tools` to contain async coroutine
* Implement async SerpaPI `arun`

Create demo notebook.

Open questions:
* Should all the async stuff go in separate classes? I've seen both
patterns (keeping the same class and having async and sync methods vs.
having class separation)

docs/modules/agents/examples/async_agent.ipynb

@@ -0,0 +1,423 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6fb92deb-d89e-439b-855d-c7f2607d794b",
+   "metadata": {},
+   "source": [
+    "# Async API for Agent\n",
+    "\n",
+    "LangChain provides async support for Agents by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
+    "\n",
+    "Async methods are currently supported for the following `Tools`: [`SerpAPIWrapper`](https://github.com/hwchase17/langchain/blob/master/langchain/serpapi.py) and [`LLMMathChain`](https://github.com/hwchase17/langchain/blob/master/langchain/chains/llm_math/base.py). Async support for other agent tools are on the roadmap.\n",
+    "\n",
+    "For `Tool`s that have a `coroutine` implemented (the two mentioned above), the `AgentExecutor` will `await` them directly. Otherwise, the `AgentExecutor` will call the `Tool`'s `func` via `asyncio.get_event_loop().run_in_executor` to avoid blocking the main runloop.\n",
+    "\n",
+    "You can use `arun` to call an `AgentExecutor` asynchronously."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97800378-cc34-4283-9bd0-43f336bc914c",
+   "metadata": {},
+   "source": [
+    "## Serial vs. Concurrent Execution\n",
+    "\n",
+    "In this example, we kick off agents to answer some questions serially vs. concurrently. You can see that concurrent execution significantly speeds this up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "da5df06c-af6f-4572-b9f5-0ab971c16487",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import asyncio\n",
+    "import time\n",
+    "\n",
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.callbacks.stdout import StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks.tracers import LangChainTracer\n",
+    "from aiohttp import ClientSession\n",
+    "\n",
+    "questions = [\n",
+    "    \"Who won the US Open men's final in 2019? What is his age raised to the 0.334 power?\",\n",
+    "    \"Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?\",\n",
+    "    \"Who won the most recent formula 1 grand prix? What is their age raised to the 0.23 power?\",\n",
+    "    \"Who won the US Open women's final in 2019? What is her age raised to the 0.34 power?\",\n",
+    "    \"Who is Beyonce's husband? What is his age raised to the 0.19 power?\"\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "fd4c294e-b1d6-44b8-b32e-2765c017e503",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
+      "Action: Search\n",
+      "Action Input: \"Rafael Nadal age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
+      "Action: Calculator\n",
+      "Action Input: 36^0.334\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis is an American actor, comedian, writer, and producer. In the 1990s, he began his career in improv comedy and performed with ComedySportz, iO Chicago, and The Second City.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' exact age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age exact\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis. (1975-09-18) September 18, 1975 (age 47). Fairfax, Virginia, U.S. · Fort Scott Community College · Actor; comedian; producer; writer · 1997– ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now have the information I need to calculate the age raised to the 0.23 power\n",
+      "Action: Calculator\n",
+      "Action Input: 47^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the grand prix and then calculate their age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Formula 1 Grand Prix Winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mMax Emilian Verstappen is a Belgian-Dutch racing driver and the 2021 and 2022 Formula One World Champion. He competes under the Dutch flag in Formula One with Red Bull Racing. Verstappen is the son of racing drivers Jos Verstappen, who also competed in Formula One, and Sophie Kumpen.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Max Emilian Verstappen's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Max Emilian Verstappen age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m25 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now need to calculate 25 raised to the 0.23 power.\n",
+      "Action: Calculator\n",
+      "Action Input: 25^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.096651272316035\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Max Emilian Verstappen, who is 25 years old, won the most recent Formula 1 Grand Prix and his age raised to the 0.23 power is 2.096651272316035.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open women's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu defeated Serena Williams in the final, 6–3, 7–5 to win the women's singles tennis title at the 2019 US Open. It was her first major title, and she became the first Canadian, as well as the first player born in the 2000s, to win a major singles title.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Bianca Andreescu's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Bianca Andreescu age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Vanessa Andreescu is a Canadian-Romanian professional tennis player. She has a career-high ranking of No. 4 in the world, and is the highest-ranked Canadian in the history of the Women's Tennis Association.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the age of Bianca Andreescu.\n",
+      "Action: Calculator\n",
+      "Action Input: 19^0.34\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.7212987634680084\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Bianca Andreescu, aged 19, won the US Open women's final in 2019. Her age raised to the 0.34 power is 2.7212987634680084.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Who is Beyonce's husband?\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJay-Z\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jay-Z's age\n",
+      "Action: Search\n",
+      "Action Input: \"How old is Jay-Z?\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m53 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 53 raised to the 0.19 power\n",
+      "Action: Calculator\n",
+      "Action Input: 53^0.19\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "Serial executed in 94.83 seconds.\n"
+     ]
+    }
+   ],
+   "source": [
+    "def generate_serially():\n",
+    "    for q in questions:\n",
+    "        llm = OpenAI(temperature=0)\n",
+    "        tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm)\n",
+    "        agent = initialize_agent(\n",
+    "            tools, llm, agent=\"zero-shot-react-description\", verbose=True\n",
+    "        )\n",
+    "        agent.run(q)\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "generate_serially()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print(f\"Serial executed in {elapsed:0.2f} seconds.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "076d7b85-45ec-465d-8b31-c2ad119c3438",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3m I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Who is Beyonce's husband?\"\u001b[0m\u001b[31;1m\u001b[1;3m I need to find out who won the grand prix and then calculate their age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Formula 1 Grand Prix Winner\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\u001b[38;5;200m\u001b[1;3m I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open women's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJay-Z\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3mMax Emilian Verstappen is a Belgian-Dutch racing driver and the 2021 and 2022 Formula One World Champion. He competes under the Dutch flag in Formula One with Red Bull Racing. Verstappen is the son of racing drivers Jos Verstappen, who also competed in Formula One, and Sophie Kumpen.\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu defeated Serena Williams in the final, 6–3, 7–5 to win the women's singles tennis title at the 2019 US Open. It was her first major title, and she became the first Canadian, as well as the first player born in the 2000s, to win a major singles title.\u001b[0m\n",
+      "Thought:\u001b[31;1m\u001b[1;3m I need to find out Max Emilian Verstappen's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Max Emilian Verstappen age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m25 years\u001b[0m\n",
+      "Thought:\u001b[38;5;200m\u001b[1;3m I need to find out Bianca Andreescu's age.\n",
+      "Action: Search\n",
+      "Action Input: \"Bianca Andreescu age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mBianca Vanessa Andreescu is a Canadian-Romanian professional tennis player. She has a career-high ranking of No. 4 in the world, and is the highest-ranked Canadian in the history of the Women's Tennis Association.\u001b[0m\n",
+      "Thought:\u001b[36;1m\u001b[1;3m I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis is an American actor, comedian, writer, and producer. In the 1990s, he began his career in improv comedy and performed with ComedySportz, iO Chicago, and The Second City.\u001b[0m\n",
+      "Thought:\u001b[33;1m\u001b[1;3m I need to find out Jay-Z's age\n",
+      "Action: Search\n",
+      "Action Input: \"How old is Jay-Z?\"\u001b[0m\u001b[36;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
+      "Action: Search\n",
+      "Action Input: \"Rafael Nadal age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[33;1m\u001b[1;3m53 years\u001b[0m\n",
+      "Thought:\u001b[38;5;200m\u001b[1;3m I now know the age of Bianca Andreescu.\n",
+      "Action: Calculator\n",
+      "Action Input: 19^0.34\u001b[0m\u001b[31;1m\u001b[1;3m I now need to calculate 25 raised to the 0.23 power.\n",
+      "Action: Calculator\n",
+      "Action Input: 25^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.7212987634680084\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' exact age\n",
+      "Action: Search\n",
+      "Action Input: \"Jason Sudeikis age exact\"\u001b[0m\u001b[33;1m\u001b[1;3m I need to calculate 53 raised to the 0.19 power\n",
+      "Action: Calculator\n",
+      "Action Input: 53^0.19\u001b[0m\u001b[36;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
+      "Action: Calculator\n",
+      "Action Input: 36^0.334\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mDaniel Jason Sudeikis. (1975-09-18) September 18, 1975 (age 47). Fairfax, Virginia, U.S. · Fort Scott Community College · Actor; comedian; producer; writer · 1997– ...\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.096651272316035\n",
+      "\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\n",
+      "\u001b[0m\n",
+      "Thought:\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now have the information I need to calculate the age raised to the 0.23 power\n",
+      "Action: Calculator\n",
+      "Action Input: 47^0.23\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Bianca Andreescu, aged 19, won the US Open women's final in 2019. Her age raised to the 0.34 power is 2.7212987634680084.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Max Emilian Verstappen, who is 25 years old, won the most recent Formula 1 Grand Prix and his age raised to the 0.23 power is 2.096651272316035.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "Concurrent executed in 25.06 seconds.\n"
+     ]
+    }
+   ],
+   "source": [
+    "async def generate_concurrently():\n",
+    "    agents = []\n",
+    "    # To make async requests in Tools more efficient, you can pass in your own aiohttp.ClientSession, \n",
+    "    # but you must manually close the client session at the end of your program/event loop\n",
+    "    aiosession = ClientSession()\n",
+    "    colors = [\"blue\", \"green\", \"red\", \"pink\", \"yellow\"]\n",
+    "    for color in colors:\n",
+    "        # Use a custom CallbackManager to print in different colors.\n",
+    "        manager = CallbackManager([StdOutCallbackHandler(color=color)])\n",
+    "        llm = OpenAI(temperature=0, callback_manager=manager)\n",
+    "        async_tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, aiosession=aiosession)\n",
+    "        agents.append(\n",
+    "            initialize_agent(async_tools, llm, agent=\"zero-shot-react-description\", verbose=True, callback_manager=manager)\n",
+    "        )\n",
+    "    tasks = [async_agent.arun(q) for async_agent, q in zip(agents, questions)]\n",
+    "    await asyncio.gather(*tasks)\n",
+    "    await aiosession.close()\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
+    "await generate_concurrently()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print(f\"Concurrent executed in {elapsed:0.2f} seconds.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97ef285c-4a43-4a4e-9698-cd52a1bc56c9",
+   "metadata": {},
+   "source": [
+    "## Using Tracing with Asynchronous Agents\n",
+    "\n",
+    "To use tracing with async agents, you must pass in a custom `CallbackManager` with `LangChainTracer` to each agent running asynchronously. This way, you avoid collisions while the trace is being collected."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "44bda05a-d33e-4e91-9a71-a0f3f96aae95",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
+      "Action: Search\n",
+      "Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
+      "Action: Search\n",
+      "Action Input: \"Rafael Nadal age\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
+      "Action: Calculator\n",
+      "Action Input: 36^0.334\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "# To make async requests in Tools more efficient, you can pass in your own aiohttp.ClientSession, \n",
+    "# but you must manually close the client session at the end of your program/event loop\n",
+    "aiosession = ClientSession()\n",
+    "tracer = LangChainTracer()\n",
+    "tracer.load_default_session()\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), tracer])\n",
+    "\n",
+    "# Pass the manager into the llm if you want llm calls traced.\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager)\n",
+    "\n",
+    "async_tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, aiosession=aiosession)\n",
+    "async_agent = initialize_agent(async_tools, llm, agent=\"zero-shot-react-description\", verbose=True, callback_manager=manager)\n",
+    "await async_agent.arun(questions[0])\n",
+    "await aiosession.close()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/agents/how_to_guides.rst

@@ -17,6 +17,7 @@ The first category of how-to guides here cover specific parts of working with ag
 
 `Max Iterations <./examples/max_iterations.html>`_: How to restrict an agent to a certain number of iterations.
 
+`Asynchronous <./examples/async_agent.html>`_: Covering asynchronous functionality.
 
 The next set of examples are all end-to-end agents for specific applications.
 In all examples there is an Agent with a particular set of tools.

docs/modules/chains/async_chain.ipynb

@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "593f7553-7038-498e-96d4-8255e5ce34f0",
+   "metadata": {},
+   "source": [
+    "# Async API for Chain\n",
+    "\n",
+    "LangChain provides async support for Chains by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
+    "\n",
+    "Async methods are currently supported in `LLMChain` (through `arun`, `apredict`, `acall`) and `LLMMathChain` (through `arun` and `acall`). Async support for other chains is on the roadmap."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c19c736e-ca74-4726-bb77-0a849bcc2960",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste Company\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste\n",
+      "\n",
+      "\n",
+      "Gleaming Smile Inc.\n",
+      "\n",
+      "\n",
+      "SparkleSmile Toothpaste\n",
+      "\u001b[1mConcurrent executed in 1.54 seconds.\u001b[0m\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "MintyFresh Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "SparkleSmile Toothpaste.\n",
+      "\n",
+      "\n",
+      "Pearly Whites Toothpaste Co.\n",
+      "\n",
+      "\n",
+      "BrightSmile Toothpaste.\n",
+      "\u001b[1mSerial executed in 6.38 seconds.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "import asyncio\n",
+    "import time\n",
+    "\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import LLMChain\n",
+    "\n",
+    "\n",
+    "def generate_serially():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    prompt = PromptTemplate(\n",
+    "        input_variables=[\"product\"],\n",
+    "        template=\"What is a good name for a company that makes {product}?\",\n",
+    "    )\n",
+    "    chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "    for _ in range(5):\n",
+    "        resp = chain.run(product=\"toothpaste\")\n",
+    "        print(resp)\n",
+    "\n",
+    "\n",
+    "async def async_generate(chain):\n",
+    "    resp = await chain.arun(product=\"toothpaste\")\n",
+    "    print(resp)\n",
+    "\n",
+    "\n",
+    "async def generate_concurrently():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    prompt = PromptTemplate(\n",
+    "        input_variables=[\"product\"],\n",
+    "        template=\"What is a good name for a company that makes {product}?\",\n",
+    "    )\n",
+    "    chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "    tasks = [async_generate(chain) for _ in range(5)]\n",
+    "    await asyncio.gather(*tasks)\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
+    "await generate_concurrently()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Concurrent executed in {elapsed:0.2f} seconds.\" + '\\033[0m')\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "generate_serially()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Serial executed in {elapsed:0.2f} seconds.\" + '\\033[0m')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/chains/how_to_guides.rst

@@ -9,6 +9,7 @@ They are broken up into three categories:
 1. `Generic Chains <./generic_how_to.html>`_: Generic chains, that are meant to help build other chains rather than serve a particular purpose.
 2. `CombineDocuments Chains <./combine_docs_how_to.html>`_: Chains aimed at making it easy to work with documents (question answering, summarization, etc).
 3. `Utility Chains <./utility_how_to.html>`_: Chains consisting of an LLMChain interacting with a specific util.
+4. `Asynchronous <./async_chain.html>`_: Covering asynchronous functionality.
 
 .. toctree::
    :maxdepth: 1

docs/modules/llms/async_llm.ipynb

@@ -0,0 +1,150 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f6574496-b360-4ffa-9523-7fd34a590164",
+   "metadata": {},
+   "source": [
+    "# Async API for LLM\n",
+    "\n",
+    "LangChain provides async support for LLMs by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
+    "\n",
+    "Async support is particularly useful for calling multiple LLMs concurrently, as these calls are network-bound. Currently, only `OpenAI` is supported, but async support for other LLMs is on the roadmap.\n",
+    "\n",
+    "You can use the `agenerate` method to call an OpenAI LLM asynchronously."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5e49e96c-0f88-466d-b3d3-ea0966bdf19e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "I'm doing well. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "I am doing quite well. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing great, thank you! How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thanks for asking. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\u001b[1mConcurrent executed in 1.93 seconds.\u001b[0m\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "\n",
+      "I'm doing great, thank you. How about you?\n",
+      "\u001b[1mSerial executed in 10.54 seconds.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "import time\n",
+    "import asyncio\n",
+    "\n",
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "def generate_serially():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    for _ in range(10):\n",
+    "        resp = llm.generate([\"Hello, how are you?\"])\n",
+    "        print(resp.generations[0][0].text)\n",
+    "\n",
+    "\n",
+    "async def async_generate(llm):\n",
+    "    resp = await llm.agenerate([\"Hello, how are you?\"])\n",
+    "    print(resp.generations[0][0].text)\n",
+    "\n",
+    "\n",
+    "async def generate_concurrently():\n",
+    "    llm = OpenAI(temperature=0.9)\n",
+    "    tasks = [async_generate(llm) for _ in range(10)]\n",
+    "    await asyncio.gather(*tasks)\n",
+    "\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
+    "await generate_concurrently() \n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Concurrent executed in {elapsed:0.2f} seconds.\" + '\\033[0m')\n",
+    "\n",
+    "s = time.perf_counter()\n",
+    "generate_serially()\n",
+    "elapsed = time.perf_counter() - s\n",
+    "print('\\033[1m' + f\"Serial executed in {elapsed:0.2f} seconds.\" + '\\033[0m')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/llms/how_to_guides.rst

@@ -7,6 +7,7 @@ They are split into two categories:
 
 1. `Generic Functionality <./generic_how_to.html>`_: Covering generic functionality all LLMs should have.
 2. `Integrations <./integrations.html>`_: Covering integrations with various LLM providers.
+3. `Asynchronous <./async_llm.html>`_: Covering asynchronous functionality.
 
 .. toctree::
    :maxdepth: 1

langchain/agents/agent.py

@@ -1,6 +1,7 @@
 """Chain that takes in an input and produces an action and action input."""
 from __future__ import annotations
 
+import asyncio
 import json
 import logging
 from abc import abstractmethod
@@ -71,6 +72,19 @@ class Agent(BaseModel):
             tool=parsed_output[0], tool_input=parsed_output[1], log=full_output
         )
 
+    async def _aget_next_action(self, full_inputs: Dict[str, str]) -> AgentAction:
+        full_output = await self.llm_chain.apredict(**full_inputs)
+        parsed_output = self._extract_tool_and_input(full_output)
+        while parsed_output is None:
+            full_output = self._fix_text(full_output)
+            full_inputs["agent_scratchpad"] += full_output
+            output = await self.llm_chain.apredict(**full_inputs)
+            full_output += output
+            parsed_output = self._extract_tool_and_input(full_output)
+        return AgentAction(
+            tool=parsed_output[0], tool_input=parsed_output[1], log=full_output
+        )
+
     def plan(
         self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any
     ) -> Union[AgentAction, AgentFinish]:
@@ -84,15 +98,40 @@ class Agent(BaseModel):
         Returns:
             Action specifying what tool to use.
         """
-        thoughts = self._construct_scratchpad(intermediate_steps)
-        new_inputs = {"agent_scratchpad": thoughts, "stop": self._stop}
-        full_inputs = {**kwargs, **new_inputs}
-
+        full_inputs = self.get_full_inputs(intermediate_steps, **kwargs)
         action = self._get_next_action(full_inputs)
         if action.tool == self.finish_tool_name:
             return AgentFinish({"output": action.tool_input}, action.log)
         return action
 
+    async def aplan(
+        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any
+    ) -> Union[AgentAction, AgentFinish]:
+        """Given input, decided what to do.
+
+        Args:
+            intermediate_steps: Steps the LLM has taken to date,
+                along with observations
+            **kwargs: User inputs.
+
+        Returns:
+            Action specifying what tool to use.
+        """
+        full_inputs = self.get_full_inputs(intermediate_steps, **kwargs)
+        action = await self._aget_next_action(full_inputs)
+        if action.tool == self.finish_tool_name:
+            return AgentFinish({"output": action.tool_input}, action.log)
+        return action
+
+    def get_full_inputs(
+        self, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any
+    ) -> Dict[str, Any]:
+        """Create the full inputs for the LLMChain from intermediate steps."""
+        thoughts = self._construct_scratchpad(intermediate_steps)
+        new_inputs = {"agent_scratchpad": thoughts, "stop": self._stop}
+        full_inputs = {**kwargs, **new_inputs}
+        return full_inputs
+
     def prepare_for_new_call(self) -> None:
         """Prepare the agent for new call, if needed."""
         pass
@@ -338,6 +377,14 @@ class AgentExecutor(Chain, BaseModel):
 
     def _call(self, inputs: Dict[str, str]) -> Dict[str, Any]:
         """Run text through and get agent response."""
+        # Make sure that every tool is synchronous (not a coroutine)
+        for tool in self.tools:
+            if asyncio.iscoroutinefunction(tool.func):
+                raise ValueError(
+                    "Tools cannot be asynchronous for `run` method. "
+                    "Please use `arun` instead."
+                )
+
         # Do any preparation necessary when receiving a new input.
         self.agent.prepare_for_new_call()
         # Construct a mapping of tool name to tool for easy lookup
@@ -399,3 +446,81 @@ class AgentExecutor(Chain, BaseModel):
             self.early_stopping_method, intermediate_steps, **inputs
         )
         return self._return(output, intermediate_steps)
+
+    async def _acall(self, inputs: Dict[str, str]) -> Dict[str, str]:
+        """Run text through and get agent response."""
+        # Make sure that every tool is asynchronous (a coroutine)
+        for tool in self.tools:
+            if tool.coroutine and not asyncio.iscoroutinefunction(tool.coroutine):
+                raise ValueError(
+                    "The coroutine for the tool must be a coroutine function."
+                )
+
+        # Do any preparation necessary when receiving a new input.
+        self.agent.prepare_for_new_call()
+        # Construct a mapping of tool name to tool for easy lookup
+        name_to_tool_map = {tool.name: tool for tool in self.tools}
+        # We construct a mapping from each tool to a color, used for logging.
+        color_mapping = get_color_mapping(
+            [tool.name for tool in self.tools], excluded_colors=["green"]
+        )
+        intermediate_steps: List[Tuple[AgentAction, str]] = []
+        # Let's start tracking the iterations the agent has gone through
+        iterations = 0
+        # We now enter the agent loop (until it returns something).
+        while self._should_continue(iterations):
+            # Call the LLM to see what to do.
+            output = await self.agent.aplan(intermediate_steps, **inputs)
+            # If the tool chosen is the finishing tool, then we end and return.
+            if isinstance(output, AgentFinish):
+                return self._return(output, intermediate_steps)
+
+            # Otherwise we lookup the tool
+            if output.tool in name_to_tool_map:
+                tool = name_to_tool_map[output.tool]
+                self.callback_manager.on_tool_start(
+                    {"name": str(tool.func)[:60] + "..."},
+                    output,
+                    verbose=self.verbose,
+                )
+                try:
+                    # We then call the tool on the tool input to get an observation
+                    observation = (
+                        await tool.coroutine(output.tool_input)
+                        if tool.coroutine
+                        # If the tool is not a coroutine, we run it in the executor
+                        # to avoid blocking the event loop.
+                        else await asyncio.get_event_loop().run_in_executor(
+                            None, tool.func, output.tool_input
+                        )
+                    )
+                    color = color_mapping[output.tool]
+                    return_direct = tool.return_direct
+                except (KeyboardInterrupt, Exception) as e:
+                    self.callback_manager.on_tool_error(e, verbose=self.verbose)
+                    raise e
+            else:
+                self.callback_manager.on_tool_start(
+                    {"name": "N/A"}, output, verbose=self.verbose
+                )
+                observation = f"{output.tool} is not a valid tool, try another one."
+                color = None
+                return_direct = False
+            llm_prefix = "" if return_direct else self.agent.llm_prefix
+            self.callback_manager.on_tool_end(
+                observation,
+                color=color,
+                observation_prefix=self.agent.observation_prefix,
+                llm_prefix=llm_prefix,
+                verbose=self.verbose,
+            )
+            intermediate_steps.append((output, observation))
+            if return_direct:
+                # Set the log to "" because we do not want to log it.
+                output = AgentFinish({self.agent.return_values[0]: observation}, "")
+                return self._return(output, intermediate_steps)
+            iterations += 1
+        output = self.agent.return_stopped_response(
+            self.early_stopping_method, intermediate_steps, **inputs
+        )
+        return self._return(output, intermediate_steps)

langchain/agents/load_tools.py

@@ -65,9 +65,10 @@ def _get_pal_colored_objects(llm: BaseLLM) -> Tool:
 
 def _get_llm_math(llm: BaseLLM) -> Tool:
     return Tool(
-        "Calculator",
-        LLMMathChain(llm=llm).run,
-        "Useful for when you need to answer questions about math.",
+        name="Calculator",
+        description="Useful for when you need to answer questions about math.",
+        func=LLMMathChain(llm=llm, callback_manager=llm.callback_manager).run,
+        coroutine=LLMMathChain(llm=llm, callback_manager=llm.callback_manager).arun,
     )
 
 
@@ -132,9 +133,10 @@ def _get_google_search(**kwargs: Any) -> Tool:
 
 def _get_serpapi(**kwargs: Any) -> Tool:
     return Tool(
-        "Search",
-        SerpAPIWrapper(**kwargs).run,
-        "A search engine. Useful for when you need to answer questions about current events. Input should be a search query.",
+        name="Search",
+        description="A search engine. Useful for when you need to answer questions about current events. Input should be a search query.",
+        func=SerpAPIWrapper(**kwargs).run,
+        coroutine=SerpAPIWrapper(**kwargs).arun,
     )
 
 
@@ -145,7 +147,7 @@ _EXTRA_LLM_TOOLS = {
 _EXTRA_OPTIONAL_TOOLS = {
     "wolfram-alpha": (_get_wolfram_alpha, ["wolfram_alpha_appid"]),
     "google-search": (_get_google_search, ["google_api_key", "google_cse_id"]),
-    "serpapi": (_get_serpapi, ["serpapi_api_key"]),
+    "serpapi": (_get_serpapi, ["serpapi_api_key", "aiosession"]),
 }
 
 

langchain/agents/tools.py

@@ -1,7 +1,8 @@
 """Interface for tools."""
+import asyncio
 from dataclasses import dataclass
 from inspect import signature
-from typing import Any, Callable, Optional, Union
+from typing import Any, Awaitable, Callable, Optional, Union
 
 
 @dataclass
@@ -12,9 +13,13 @@ class Tool:
     func: Callable[[str], str]
     description: Optional[str] = None
     return_direct: bool = False
+    # If the tool has a coroutine, then we can use this to run it asynchronously
+    coroutine: Optional[Callable[[str], Awaitable[str]]] = None
 
     def __call__(self, *args: Any, **kwargs: Any) -> str:
         """Make tools callable by piping through to `func`."""
+        if asyncio.iscoroutinefunction(self.func):
+            raise TypeError("Coroutine cannot be called directly")
         return self.func(*args, **kwargs)
 
 

langchain/callbacks/stdout.py

@@ -9,6 +9,10 @@ from langchain.schema import AgentAction, AgentFinish, LLMResult
 class StdOutCallbackHandler(BaseCallbackHandler):
     """Callback Handler that prints to std out."""
 
+    def __init__(self, color: str = "green") -> None:
+        """Initialize callback handler."""
+        self.color = color
+
     def on_llm_start(
         self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
     ) -> None:
@@ -50,7 +54,7 @@ class StdOutCallbackHandler(BaseCallbackHandler):
         **kwargs: Any,
     ) -> None:
         """Print out the log in specified color."""
-        print_text(action.log, color=color)
+        print_text(action.log, color=color if color else self.color)
 
     def on_tool_end(
         self,
@@ -62,7 +66,7 @@ class StdOutCallbackHandler(BaseCallbackHandler):
     ) -> None:
         """If not the final action, print out observation."""
         print_text(f"\n{observation_prefix}")
-        print_text(output, color=color)
+        print_text(output, color=color if color else self.color)
         print_text(f"\n{llm_prefix}")
 
     def on_tool_error(
@@ -79,10 +83,10 @@ class StdOutCallbackHandler(BaseCallbackHandler):
         **kwargs: Optional[str],
     ) -> None:
         """Run when agent ends."""
-        print_text(text, color=color, end=end)
+        print_text(text, color=color if color else self.color, end=end)
 
     def on_agent_finish(
         self, finish: AgentFinish, color: Optional[str] = None, **kwargs: Any
     ) -> None:
         """Run on agent end."""
-        print_text(finish.log, color=color, end="\n")
+        print_text(finish.log, color=color if self.color else color, end="\n")

langchain/chains/base.py

@@ -111,6 +111,10 @@ class Chain(BaseModel, ABC):
     def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
         """Run the logic of this chain and return the output."""
 
+    async def _acall(self, inputs: Dict[str, str]) -> Dict[str, str]:
+        """Run the logic of this chain and return the output."""
+        raise NotImplementedError("Async call not supported for this chain type.")
+
     def __call__(
         self, inputs: Union[Dict[str, Any], Any], return_only_outputs: bool = False
     ) -> Dict[str, Any]:
@@ -125,24 +129,7 @@ class Chain(BaseModel, ABC):
                 chain will be returned. Defaults to False.
 
         """
-        if not isinstance(inputs, dict):
-            _input_keys = set(self.input_keys)
-            if self.memory is not None:
-                # If there are multiple input keys, but some get set by memory so that
-                # only one is not set, we can still figure out which key it is.
-                _input_keys = _input_keys.difference(self.memory.memory_variables)
-            if len(_input_keys) != 1:
-                raise ValueError(
-                    f"A single string input was passed in, but this chain expects "
-                    f"multiple inputs ({_input_keys}). When a chain expects "
-                    f"multiple inputs, please call it by passing in a dictionary, "
-                    "eg `chain({'foo': 1, 'bar': 2})`"
-                )
-            inputs = {list(_input_keys)[0]: inputs}
-        if self.memory is not None:
-            external_context = self.memory.load_memory_variables(inputs)
-            inputs = dict(inputs, **external_context)
-        self._validate_inputs(inputs)
+        inputs = self.prep_inputs(inputs)
         self.callback_manager.on_chain_start(
             {"name": self.__class__.__name__},
             inputs,
@@ -154,6 +141,43 @@ class Chain(BaseModel, ABC):
             self.callback_manager.on_chain_error(e, verbose=self.verbose)
             raise e
         self.callback_manager.on_chain_end(outputs, verbose=self.verbose)
+        return self.prep_outputs(inputs, outputs, return_only_outputs)
+
+    async def acall(
+        self, inputs: Union[Dict[str, Any], Any], return_only_outputs: bool = False
+    ) -> Dict[str, Any]:
+        """Run the logic of this chain and add to output if desired.
+
+        Args:
+            inputs: Dictionary of inputs, or single input if chain expects
+                only one param.
+            return_only_outputs: boolean for whether to return only outputs in the
+                response. If True, only new keys generated by this chain will be
+                returned. If False, both input keys and new keys generated by this
+                chain will be returned. Defaults to False.
+
+        """
+        inputs = self.prep_inputs(inputs)
+        self.callback_manager.on_chain_start(
+            {"name": self.__class__.__name__},
+            inputs,
+            verbose=self.verbose,
+        )
+        try:
+            outputs = await self._acall(inputs)
+        except (KeyboardInterrupt, Exception) as e:
+            self.callback_manager.on_chain_error(e, verbose=self.verbose)
+            raise e
+        self.callback_manager.on_chain_end(outputs, verbose=self.verbose)
+        return self.prep_outputs(inputs, outputs, return_only_outputs)
+
+    def prep_outputs(
+        self,
+        inputs: Dict[str, str],
+        outputs: Dict[str, str],
+        return_only_outputs: bool = False,
+    ) -> Dict[str, str]:
+        """Validate and prep outputs."""
         self._validate_outputs(outputs)
         if self.memory is not None:
             self.memory.save_context(inputs, outputs)
@@ -162,6 +186,28 @@ class Chain(BaseModel, ABC):
         else:
             return {**inputs, **outputs}
 
+    def prep_inputs(self, inputs: Union[Dict[str, Any], Any]) -> Dict[str, str]:
+        """Validate and prep inputs."""
+        if not isinstance(inputs, dict):
+            _input_keys = set(self.input_keys)
+            if self.memory is not None:
+                # If there are multiple input keys, but some get set by memory so that
+                # only one is not set, we can still figure out which key it is.
+                _input_keys = _input_keys.difference(self.memory.memory_variables)
+            if len(_input_keys) != 1:
+                raise ValueError(
+                    f"A single string input was passed in, but this chain expects "
+                    f"multiple inputs ({_input_keys}). When a chain expects "
+                    f"multiple inputs, please call it by passing in a dictionary, "
+                    "eg `chain({'foo': 1, 'bar': 2})`"
+                )
+            inputs = {list(_input_keys)[0]: inputs}
+        if self.memory is not None:
+            external_context = self.memory.load_memory_variables(inputs)
+            inputs = dict(inputs, **external_context)
+        self._validate_inputs(inputs)
+        return inputs
+
     def apply(self, input_list: List[Dict[str, Any]]) -> List[Dict[str, str]]:
         """Call the chain on all inputs in the list."""
         return [self(inputs) for inputs in input_list]
@@ -187,6 +233,27 @@ class Chain(BaseModel, ABC):
             f" but not both. Got args: {args} and kwargs: {kwargs}."
         )
 
+    async def arun(self, *args: str, **kwargs: str) -> str:
+        """Run the chain as text in, text out or multiple variables, text out."""
+        if len(self.output_keys) != 1:
+            raise ValueError(
+                f"`run` not supported when there is not exactly "
+                f"one output key. Got {self.output_keys}."
+            )
+
+        if args and not kwargs:
+            if len(args) != 1:
+                raise ValueError("`run` supports only one positional argument.")
+            return (await self.acall(args[0]))[self.output_keys[0]]
+
+        if kwargs and not args:
+            return (await self.acall(kwargs))[self.output_keys[0]]
+
+        raise ValueError(
+            f"`run` supported with either positional arguments or keyword arguments"
+            f" but not both. Got args: {args} and kwargs: {kwargs}."
+        )
+
     def dict(self, **kwargs: Any) -> Dict:
         """Return dictionary representation of chain."""
         if self.memory is not None:

langchain/chains/llm.py

@@ -1,5 +1,5 @@
 """Chain that just formats a prompt and calls an LLM."""
-from typing import Any, Dict, List, Sequence, Union
+from typing import Any, Dict, List, Optional, Sequence, Tuple, Union
 
 from pydantic import BaseModel, Extra
 
@@ -55,6 +55,20 @@ class LLMChain(Chain, BaseModel):
 
     def generate(self, input_list: List[Dict[str, Any]]) -> LLMResult:
         """Generate LLM result from inputs."""
+        prompts, stop = self.prep_prompts(input_list)
+        response = self.llm.generate(prompts, stop=stop)
+        return response
+
+    async def agenerate(self, input_list: List[Dict[str, Any]]) -> LLMResult:
+        """Generate LLM result from inputs."""
+        prompts, stop = self.prep_prompts(input_list)
+        response = await self.llm.agenerate(prompts, stop=stop)
+        return response
+
+    def prep_prompts(
+        self, input_list: List[Dict[str, Any]]
+    ) -> Tuple[List[str], Optional[List[str]]]:
+        """Prepare prompts from inputs."""
         stop = None
         if "stop" in input_list[0]:
             stop = input_list[0]["stop"]
@@ -70,12 +84,20 @@ class LLMChain(Chain, BaseModel):
                     "If `stop` is present in any inputs, should be present in all."
                 )
             prompts.append(prompt)
-        response = self.llm.generate(prompts, stop=stop)
-        return response
+        return prompts, stop
 
     def apply(self, input_list: List[Dict[str, Any]]) -> List[Dict[str, str]]:
         """Utilize the LLM generate method for speed gains."""
         response = self.generate(input_list)
+        return self.create_outputs(response)
+
+    async def aapply(self, input_list: List[Dict[str, Any]]) -> List[Dict[str, str]]:
+        """Utilize the LLM generate method for speed gains."""
+        response = await self.agenerate(input_list)
+        return self.create_outputs(response)
+
+    def create_outputs(self, response: LLMResult) -> List[Dict[str, str]]:
+        """Create outputs from response."""
         outputs = []
         for generation in response.generations:
             # Get the text of the top generated string.
@@ -86,6 +108,9 @@ class LLMChain(Chain, BaseModel):
     def _call(self, inputs: Dict[str, Any]) -> Dict[str, str]:
         return self.apply([inputs])[0]
 
+    async def _acall(self, inputs: Dict[str, Any]) -> Dict[str, str]:
+        return (await self.aapply([inputs]))[0]
+
     def predict(self, **kwargs: Any) -> str:
         """Format prompt with kwargs and pass to LLM.
 
@@ -102,6 +127,22 @@ class LLMChain(Chain, BaseModel):
         """
         return self(kwargs)[self.output_key]
 
+    async def apredict(self, **kwargs: Any) -> str:
+        """Format prompt with kwargs and pass to LLM.
+
+        Args:
+            **kwargs: Keys to pass to prompt template.
+
+        Returns:
+            Completion from LLM.
+
+        Example:
+            .. code-block:: python
+
+                completion = llm.predict(adjective="funny")
+        """
+        return (await self.acall(kwargs))[self.output_key]
+
     def predict_and_parse(self, **kwargs: Any) -> Union[str, List[str], Dict[str, str]]:
         """Call predict and then parse the results."""
         result = self.predict(**kwargs)

langchain/chains/llm_math/base.py

@@ -50,11 +50,8 @@ class LLMMathChain(Chain, BaseModel):
         """
         return [self.output_key]
 
-    def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
-        llm_executor = LLMChain(prompt=self.prompt, llm=self.llm)
+    def _process_llm_result(self, t: str) -> Dict[str, str]:
         python_executor = PythonREPL()
-        self.callback_manager.on_text(inputs[self.input_key], verbose=self.verbose)
-        t = llm_executor.predict(question=inputs[self.input_key], stop=["```output"])
         self.callback_manager.on_text(t, color="green", verbose=self.verbose)
         t = t.strip()
         if t.startswith("```python"):
@@ -69,6 +66,24 @@ class LLMMathChain(Chain, BaseModel):
             raise ValueError(f"unknown format from LLM: {t}")
         return {self.output_key: answer}
 
+    def _call(self, inputs: Dict[str, str]) -> Dict[str, str]:
+        llm_executor = LLMChain(
+            prompt=self.prompt, llm=self.llm, callback_manager=self.callback_manager
+        )
+        self.callback_manager.on_text(inputs[self.input_key], verbose=self.verbose)
+        t = llm_executor.predict(question=inputs[self.input_key], stop=["```output"])
+        return self._process_llm_result(t)
+
+    async def _acall(self, inputs: Dict[str, str]) -> Dict[str, str]:
+        llm_executor = LLMChain(
+            prompt=self.prompt, llm=self.llm, callback_manager=self.callback_manager
+        )
+        self.callback_manager.on_text(inputs[self.input_key], verbose=self.verbose)
+        t = await llm_executor.apredict(
+            question=inputs[self.input_key], stop=["```output"]
+        )
+        return self._process_llm_result(t)
+
     @property
     def _chain_type(self) -> str:
         return "llm_math_chain"

langchain/input.py

@@ -6,6 +6,7 @@ _TEXT_COLOR_MAPPING = {
     "yellow": "33;1",
     "pink": "38;5;200",
     "green": "32;1",
+    "red": "31;1",
 }
 
 

langchain/llms/base.py

@@ -2,7 +2,7 @@
 import json
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Any, Dict, List, Mapping, Optional, Union
+from typing import Any, Dict, List, Mapping, Optional, Tuple, Union
 
 import yaml
 from pydantic import BaseModel, Extra, Field, validator
@@ -17,6 +17,42 @@ def _get_verbosity() -> bool:
     return langchain.verbose
 
 
+def get_prompts(
+    params: Dict[str, Any], prompts: List[str]
+) -> Tuple[Dict[int, List], str, List[int], List[str]]:
+    """Get prompts that are already cached."""
+    llm_string = str(sorted([(k, v) for k, v in params.items()]))
+    missing_prompts = []
+    missing_prompt_idxs = []
+    existing_prompts = {}
+    for i, prompt in enumerate(prompts):
+        if langchain.llm_cache is not None:
+            cache_val = langchain.llm_cache.lookup(prompt, llm_string)
+            if isinstance(cache_val, list):
+                existing_prompts[i] = cache_val
+            else:
+                missing_prompts.append(prompt)
+                missing_prompt_idxs.append(i)
+    return existing_prompts, llm_string, missing_prompt_idxs, missing_prompts
+
+
+def update_cache(
+    existing_prompts: Dict[int, List],
+    llm_string: str,
+    missing_prompt_idxs: List[int],
+    new_results: LLMResult,
+    prompts: List[str],
+) -> Optional[dict]:
+    """Update the cache and get the LLM output."""
+    for i, result in enumerate(new_results.generations):
+        existing_prompts[missing_prompt_idxs[i]] = result
+        prompt = prompts[missing_prompt_idxs[i]]
+        if langchain.llm_cache is not None:
+            langchain.llm_cache.update(prompt, llm_string, result)
+    llm_output = new_results.llm_output
+    return llm_output
+
+
 class BaseLLM(BaseModel, ABC):
     """LLM wrapper should take in a prompt and return a string."""
 
@@ -58,6 +94,12 @@ class BaseLLM(BaseModel, ABC):
     ) -> LLMResult:
         """Run the LLM on the given prompts."""
 
+    @abstractmethod
+    async def _agenerate(
+        self, prompts: List[str], stop: Optional[List[str]] = None
+    ) -> LLMResult:
+        """Run the LLM on the given prompts."""
+
     def generate(
         self, prompts: List[str], stop: Optional[List[str]] = None
     ) -> LLMResult:
@@ -88,17 +130,12 @@ class BaseLLM(BaseModel, ABC):
             return output
         params = self.dict()
         params["stop"] = stop
-        llm_string = str(sorted([(k, v) for k, v in params.items()]))
-        missing_prompts = []
-        missing_prompt_idxs = []
-        existing_prompts = {}
-        for i, prompt in enumerate(prompts):
-            cache_val = langchain.llm_cache.lookup(prompt, llm_string)
-            if isinstance(cache_val, list):
-                existing_prompts[i] = cache_val
-            else:
-                missing_prompts.append(prompt)
-                missing_prompt_idxs.append(i)
+        (
+            existing_prompts,
+            llm_string,
+            missing_prompt_idxs,
+            missing_prompts,
+        ) = get_prompts(params, prompts)
         if len(missing_prompts) > 0:
             self.callback_manager.on_llm_start(
                 {"name": self.__class__.__name__}, missing_prompts, verbose=self.verbose
@@ -109,11 +146,56 @@ class BaseLLM(BaseModel, ABC):
                 self.callback_manager.on_llm_error(e, verbose=self.verbose)
                 raise e
             self.callback_manager.on_llm_end(new_results, verbose=self.verbose)
-            for i, result in enumerate(new_results.generations):
-                existing_prompts[missing_prompt_idxs[i]] = result
-                prompt = prompts[missing_prompt_idxs[i]]
-                langchain.llm_cache.update(prompt, llm_string, result)
-            llm_output = new_results.llm_output
+            llm_output = update_cache(
+                existing_prompts, llm_string, missing_prompt_idxs, new_results, prompts
+            )
+        else:
+            llm_output = {}
+        generations = [existing_prompts[i] for i in range(len(prompts))]
+        return LLMResult(generations=generations, llm_output=llm_output)
+
+    async def agenerate(
+        self, prompts: List[str], stop: Optional[List[str]] = None
+    ) -> LLMResult:
+        """Run the LLM on the given prompt and input."""
+        disregard_cache = self.cache is not None and not self.cache
+        if langchain.llm_cache is None or disregard_cache:
+            # This happens when langchain.cache is None, but self.cache is True
+            if self.cache is not None and self.cache:
+                raise ValueError(
+                    "Asked to cache, but no cache found at `langchain.cache`."
+                )
+            self.callback_manager.on_llm_start(
+                {"name": self.__class__.__name__}, prompts, verbose=self.verbose
+            )
+            try:
+                output = await self._agenerate(prompts, stop=stop)
+            except (KeyboardInterrupt, Exception) as e:
+                self.callback_manager.on_llm_error(e, verbose=self.verbose)
+                raise e
+            self.callback_manager.on_llm_end(output, verbose=self.verbose)
+            return output
+        params = self.dict()
+        params["stop"] = stop
+        (
+            existing_prompts,
+            llm_string,
+            missing_prompt_idxs,
+            missing_prompts,
+        ) = get_prompts(params, prompts)
+        if len(missing_prompts) > 0:
+            self.callback_manager.on_llm_start(
+                {"name": self.__class__.__name__}, missing_prompts, verbose=self.verbose
+            )
+            try:
+                new_results = await self._agenerate(missing_prompts, stop=stop)
+            except (KeyboardInterrupt, Exception) as e:
+                self.callback_manager.on_llm_error(e, verbose=self.verbose)
+                raise e
+            self.callback_manager.on_llm_end(new_results, verbose=self.verbose)
+            llm_output = update_cache(
+                existing_prompts, llm_string, missing_prompt_idxs, new_results, prompts
+            )
         else:
             llm_output = {}
         generations = [existing_prompts[i] for i in range(len(prompts))]
@@ -219,3 +301,9 @@ class LLM(BaseLLM):
             text = self._call(prompt, stop=stop)
             generations.append([Generation(text=text)])
         return LLMResult(generations=generations)
+
+    async def _agenerate(
+        self, prompts: List[str], stop: Optional[List[str]] = None
+    ) -> LLMResult:
+        """Run the LLM on the given prompt and input."""
+        raise NotImplementedError("Async generation not implemented for this LLM.")

langchain/llms/openai.py

@@ -1,11 +1,22 @@
 """Wrapper around OpenAI APIs."""
 import logging
 import sys
-from typing import Any, Dict, Generator, List, Mapping, Optional, Tuple, Union
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    Generator,
+    List,
+    Mapping,
+    Optional,
+    Set,
+    Tuple,
+    Union,
+)
 
 from pydantic import BaseModel, Extra, Field, root_validator
 from tenacity import (
-    after_log,
+    before_sleep_log,
     retry,
     retry_if_exception_type,
     stop_after_attempt,
@@ -19,6 +30,18 @@ from langchain.utils import get_from_dict_or_env
 logger = logging.getLogger(__name__)
 
 
+def update_token_usage(
+    keys: Set[str], response: Dict[str, Any], token_usage: Dict[str, Any]
+) -> None:
+    """Update token usage."""
+    _keys_to_use = keys.intersection(response["usage"])
+    for _key in _keys_to_use:
+        if _key not in token_usage:
+            token_usage[_key] = response["usage"][_key]
+        else:
+            token_usage[_key] += response["usage"][_key]
+
+
 class BaseOpenAI(BaseLLM, BaseModel):
     """Wrapper around OpenAI large language models.
 
@@ -124,16 +147,14 @@ class BaseOpenAI(BaseLLM, BaseModel):
         }
         return {**normal_params, **self.model_kwargs}
 
-    def completion_with_retry(self, **kwargs: Any) -> Any:
-        """Use tenacity to retry the completion call."""
+    def _create_retry_decorator(self) -> Callable[[Any], Any]:
         import openai
 
         min_seconds = 4
         max_seconds = 10
         # Wait 2^x * 1 second between each retry starting with
         # 4 seconds, then up to 10 seconds, then 10 seconds afterwards
-
-        @retry(
+        return retry(
             reraise=True,
             stop=stop_after_attempt(self.max_retries),
             wait=wait_exponential(multiplier=1, min=min_seconds, max=max_seconds),
@@ -143,13 +164,30 @@ class BaseOpenAI(BaseLLM, BaseModel):
                 | retry_if_exception_type(openai.error.APIConnectionError)
                 | retry_if_exception_type(openai.error.RateLimitError)
             ),
-            after=after_log(logger, logging.DEBUG),
+            before_sleep=before_sleep_log(logger, logging.WARNING),
         )
+
+    def completion_with_retry(self, **kwargs: Any) -> Any:
+        """Use tenacity to retry the completion call."""
+        retry_decorator = self._create_retry_decorator()
+
+        @retry_decorator
         def _completion_with_retry(**kwargs: Any) -> Any:
             return self.client.create(**kwargs)
 
         return _completion_with_retry(**kwargs)
 
+    async def acompletion_with_retry(self, **kwargs: Any) -> Any:
+        """Use tenacity to retry the async completion call."""
+        retry_decorator = self._create_retry_decorator()
+
+        @retry_decorator
+        async def _completion_with_retry(**kwargs: Any) -> Any:
+            # Use OpenAI's async api https://github.com/openai/openai-python#async-api
+            return await self.client.acreate(**kwargs)
+
+        return await _completion_with_retry(**kwargs)
+
     def _generate(
         self, prompts: List[str], stop: Optional[List[str]] = None
     ) -> LLMResult:
@@ -169,11 +207,47 @@ class BaseOpenAI(BaseLLM, BaseModel):
         """
         # TODO: write a unit test for this
         params = self._invocation_params
+        sub_prompts = self.get_sub_prompts(params, prompts, stop)
+        choices = []
+        token_usage: Dict[str, int] = {}
+        # Get the token usage from the response.
+        # Includes prompt, completion, and total tokens used.
+        _keys = {"completion_tokens", "prompt_tokens", "total_tokens"}
+        for _prompts in sub_prompts:
+            response = self.completion_with_retry(prompt=_prompts, **params)
+            choices.extend(response["choices"])
+            update_token_usage(_keys, response, token_usage)
+        return self.create_llm_result(choices, prompts, token_usage)
+
+    async def _agenerate(
+        self, prompts: List[str], stop: Optional[List[str]] = None
+    ) -> LLMResult:
+        """Call out to OpenAI's endpoint async with k unique prompts."""
+        params = self._invocation_params
+        sub_prompts = self.get_sub_prompts(params, prompts, stop)
+        choices = []
+        token_usage: Dict[str, int] = {}
+        # Get the token usage from the response.
+        # Includes prompt, completion, and total tokens used.
+        _keys = {"completion_tokens", "prompt_tokens", "total_tokens"}
+        for _prompts in sub_prompts:
+            # Use OpenAI's async api https://github.com/openai/openai-python#async-api
+            response = await self.acompletion_with_retry(prompt=_prompts, **params)
+            choices.extend(response["choices"])
+            update_token_usage(_keys, response, token_usage)
+        return self.create_llm_result(choices, prompts, token_usage)
+
+    def get_sub_prompts(
+        self,
+        params: Dict[str, Any],
+        prompts: List[str],
+        stop: Optional[List[str]] = None,
+    ) -> List[List[str]]:
+        """Get the sub prompts for llm call."""
         if stop is not None:
             if "stop" in params:
                 raise ValueError("`stop` found in both the input and default params.")
             params["stop"] = stop
-
         if params["max_tokens"] == -1:
             if len(prompts) != 1:
                 raise ValueError(
@@ -184,20 +258,12 @@ class BaseOpenAI(BaseLLM, BaseModel):
             prompts[i : i + self.batch_size]
             for i in range(0, len(prompts), self.batch_size)
         ]
-        choices = []
-        token_usage = {}
-        # Get the token usage from the response.
-        # Includes prompt, completion, and total tokens used.
-        _keys = {"completion_tokens", "prompt_tokens", "total_tokens"}
-        for _prompts in sub_prompts:
-            response = self.completion_with_retry(prompt=_prompts, **params)
-            choices.extend(response["choices"])
-            _keys_to_use = _keys.intersection(response["usage"])
-            for _key in _keys_to_use:
-                if _key not in token_usage:
-                    token_usage[_key] = response["usage"][_key]
-                else:
-                    token_usage[_key] += response["usage"][_key]
+        return sub_prompts
+
+    def create_llm_result(
+        self, choices: Any, prompts: List[str], token_usage: Dict[str, int]
+    ) -> LLMResult:
+        """Create the LLMResult from the choices and prompts."""
         generations = []
         for i, prompt in enumerate(prompts):
             sub_choices = choices[i * self.n : (i + 1) * self.n]

langchain/serpapi.py

@@ -4,8 +4,9 @@ Heavily borrowed from https://github.com/ofirpress/self-ask
 """
 import os
 import sys
-from typing import Any, Dict, Optional
+from typing import Any, Dict, Optional, Tuple
 
+import aiohttp
 from pydantic import BaseModel, Extra, Field, root_validator
 
 from langchain.utils import get_from_dict_or_env
@@ -34,6 +35,37 @@ def _get_default_params() -> dict:
     }
 
 
+def process_response(res: dict) -> str:
+    """Process response from SerpAPI."""
+    if "error" in res.keys():
+        raise ValueError(f"Got error from SerpAPI: {res['error']}")
+    if "answer_box" in res.keys() and "answer" in res["answer_box"].keys():
+        toret = res["answer_box"]["answer"]
+    elif "answer_box" in res.keys() and "snippet" in res["answer_box"].keys():
+        toret = res["answer_box"]["snippet"]
+    elif (
+        "answer_box" in res.keys()
+        and "snippet_highlighted_words" in res["answer_box"].keys()
+    ):
+        toret = res["answer_box"]["snippet_highlighted_words"][0]
+    elif (
+        "sports_results" in res.keys()
+        and "game_spotlight" in res["sports_results"].keys()
+    ):
+        toret = res["sports_results"]["game_spotlight"]
+    elif (
+        "knowledge_graph" in res.keys()
+        and "description" in res["knowledge_graph"].keys()
+    ):
+        toret = res["knowledge_graph"]["description"]
+    elif "snippet" in res["organic_results"][0].keys():
+        toret = res["organic_results"][0]["snippet"]
+
+    else:
+        toret = "No good search result found"
+    return toret
+
+
 class SerpAPIWrapper(BaseModel):
     """Wrapper around SerpAPI.
 
@@ -51,11 +83,13 @@ class SerpAPIWrapper(BaseModel):
     search_engine: Any  #: :meta private:
     params: dict = Field(default_factory=_get_default_params)
     serpapi_api_key: Optional[str] = None
+    aiosession: Optional[aiohttp.ClientSession] = None
 
     class Config:
         """Configuration for this pydantic object."""
 
         extra = Extra.forbid
+        arbitrary_types_allowed = True
 
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:
@@ -75,45 +109,47 @@ class SerpAPIWrapper(BaseModel):
             )
         return values
 
+    async def arun(self, query: str) -> str:
+        """Use aiohttp to run query through SerpAPI and parse result."""
+
+        def construct_url_and_params() -> Tuple[str, Dict[str, str]]:
+            params = self.get_params(query)
+            params["source"] = "python"
+            if self.serpapi_api_key:
+                params["serp_api_key"] = self.serpapi_api_key
+            params["output"] = "json"
+            url = "https://serpapi.com/search"
+            return url, params
+
+        url, params = construct_url_and_params()
+        if not self.aiosession:
+            async with aiohttp.ClientSession() as session:
+                async with session.get(url, params=params) as response:
+                    res = await response.json()
+        else:
+            async with self.aiosession.get(url, params=params) as response:
+                res = await response.json()
+
+        return process_response(res)
+
     def run(self, query: str) -> str:
         """Run query through SerpAPI and parse result."""
+        params = self.get_params(query)
+        with HiddenPrints():
+            search = self.search_engine(params)
+            res = search.get_dict()
+        return process_response(res)
+
+    def get_params(self, query: str) -> Dict[str, str]:
+        """Get parameters for SerpAPI."""
         _params = {
             "api_key": self.serpapi_api_key,
             "q": query,
         }
         params = {**self.params, **_params}
-        with HiddenPrints():
-            search = self.search_engine(params)
-            res = search.get_dict()
-        if "error" in res.keys():
-            raise ValueError(f"Got error from SerpAPI: {res['error']}")
-        if "answer_box" in res.keys() and "answer" in res["answer_box"].keys():
-            toret = res["answer_box"]["answer"]
-        elif "answer_box" in res.keys() and "snippet" in res["answer_box"].keys():
-            toret = res["answer_box"]["snippet"]
-        elif (
-            "answer_box" in res.keys()
-            and "snippet_highlighted_words" in res["answer_box"].keys()
-        ):
-            toret = res["answer_box"]["snippet_highlighted_words"][0]
-        elif (
-            "sports_results" in res.keys()
-            and "game_spotlight" in res["sports_results"].keys()
-        ):
-            toret = res["sports_results"]["game_spotlight"]
-        elif (
-            "knowledge_graph" in res.keys()
-            and "description" in res["knowledge_graph"].keys()
-        ):
-            toret = res["knowledge_graph"]["description"]
-        elif "snippet" in res["organic_results"][0].keys():
-            toret = res["organic_results"][0]["snippet"]
-
-        else:
-            toret = "No good search result found"
-        return toret
+        return params
 
 
-# For backwards compatability
+# For backwards compatibility
 
 SerpAPIChain = SerpAPIWrapper

poetry.lock

@@ -12,6 +12,130 @@ files = [
     {file = "absl_py-1.4.0-py3-none-any.whl", hash = "sha256:0d3fe606adfa4f7db64792dd4c7aee4ee0c38ab75dfd353b7a83ed3e957fcb47"},
 ]
 
+[[package]]
+name = "aiohttp"
+version = "3.8.3"
+description = "Async http client/server framework (asyncio)"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "aiohttp-3.8.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ba71c9b4dcbb16212f334126cc3d8beb6af377f6703d9dc2d9fb3874fd667ee9"},
+    {file = "aiohttp-3.8.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d24b8bb40d5c61ef2d9b6a8f4528c2f17f1c5d2d31fed62ec860f6006142e83e"},
+    {file = "aiohttp-3.8.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f88df3a83cf9df566f171adba39d5bd52814ac0b94778d2448652fc77f9eb491"},
+    {file = "aiohttp-3.8.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b97decbb3372d4b69e4d4c8117f44632551c692bb1361b356a02b97b69e18a62"},
+    {file = "aiohttp-3.8.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:309aa21c1d54b8ef0723181d430347d7452daaff93e8e2363db8e75c72c2fb2d"},
+    {file = "aiohttp-3.8.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ad5383a67514e8e76906a06741febd9126fc7c7ff0f599d6fcce3e82b80d026f"},
+    {file = "aiohttp-3.8.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:20acae4f268317bb975671e375493dbdbc67cddb5f6c71eebdb85b34444ac46b"},
+    {file = "aiohttp-3.8.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:05a3c31c6d7cd08c149e50dc7aa2568317f5844acd745621983380597f027a18"},
+    {file = "aiohttp-3.8.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d6f76310355e9fae637c3162936e9504b4767d5c52ca268331e2756e54fd4ca5"},
+    {file = "aiohttp-3.8.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:256deb4b29fe5e47893fa32e1de2d73c3afe7407738bd3c63829874661d4822d"},
+    {file = "aiohttp-3.8.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:5c59fcd80b9049b49acd29bd3598cada4afc8d8d69bd4160cd613246912535d7"},
+    {file = "aiohttp-3.8.3-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:059a91e88f2c00fe40aed9031b3606c3f311414f86a90d696dd982e7aec48142"},
+    {file = "aiohttp-3.8.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:2feebbb6074cdbd1ac276dbd737b40e890a1361b3cc30b74ac2f5e24aab41f7b"},
+    {file = "aiohttp-3.8.3-cp310-cp310-win32.whl", hash = "sha256:5bf651afd22d5f0c4be16cf39d0482ea494f5c88f03e75e5fef3a85177fecdeb"},
+    {file = "aiohttp-3.8.3-cp310-cp310-win_amd64.whl", hash = "sha256:653acc3880459f82a65e27bd6526e47ddf19e643457d36a2250b85b41a564715"},
+    {file = "aiohttp-3.8.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:86fc24e58ecb32aee09f864cb11bb91bc4c1086615001647dbfc4dc8c32f4008"},
+    {file = "aiohttp-3.8.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:75e14eac916f024305db517e00a9252714fce0abcb10ad327fb6dcdc0d060f1d"},
+    {file = "aiohttp-3.8.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d1fde0f44029e02d02d3993ad55ce93ead9bb9b15c6b7ccd580f90bd7e3de476"},
+    {file = "aiohttp-3.8.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ab94426ddb1ecc6a0b601d832d5d9d421820989b8caa929114811369673235c"},
+    {file = "aiohttp-3.8.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:89d2e02167fa95172c017732ed7725bc8523c598757f08d13c5acca308e1a061"},
+    {file = "aiohttp-3.8.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:02f9a2c72fc95d59b881cf38a4b2be9381b9527f9d328771e90f72ac76f31ad8"},
+    {file = "aiohttp-3.8.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9c7149272fb5834fc186328e2c1fa01dda3e1fa940ce18fded6d412e8f2cf76d"},
+    {file = "aiohttp-3.8.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:512bd5ab136b8dc0ffe3fdf2dfb0c4b4f49c8577f6cae55dca862cd37a4564e2"},
+    {file = "aiohttp-3.8.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:7018ecc5fe97027214556afbc7c502fbd718d0740e87eb1217b17efd05b3d276"},
+    {file = "aiohttp-3.8.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:88c70ed9da9963d5496d38320160e8eb7e5f1886f9290475a881db12f351ab5d"},
+    {file = "aiohttp-3.8.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:da22885266bbfb3f78218dc40205fed2671909fbd0720aedba39b4515c038091"},
+    {file = "aiohttp-3.8.3-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:e65bc19919c910127c06759a63747ebe14f386cda573d95bcc62b427ca1afc73"},
+    {file = "aiohttp-3.8.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:08c78317e950e0762c2983f4dd58dc5e6c9ff75c8a0efeae299d363d439c8e34"},
+    {file = "aiohttp-3.8.3-cp311-cp311-win32.whl", hash = "sha256:45d88b016c849d74ebc6f2b6e8bc17cabf26e7e40c0661ddd8fae4c00f015697"},
+    {file = "aiohttp-3.8.3-cp311-cp311-win_amd64.whl", hash = "sha256:96372fc29471646b9b106ee918c8eeb4cca423fcbf9a34daa1b93767a88a2290"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:c971bf3786b5fad82ce5ad570dc6ee420f5b12527157929e830f51c55dc8af77"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ff25f48fc8e623d95eca0670b8cc1469a83783c924a602e0fbd47363bb54aaca"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e381581b37db1db7597b62a2e6b8b57c3deec95d93b6d6407c5b61ddc98aca6d"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:db19d60d846283ee275d0416e2a23493f4e6b6028825b51290ac05afc87a6f97"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:25892c92bee6d9449ffac82c2fe257f3a6f297792cdb18ad784737d61e7a9a85"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:398701865e7a9565d49189f6c90868efaca21be65c725fc87fc305906be915da"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:4a4fbc769ea9b6bd97f4ad0b430a6807f92f0e5eb020f1e42ece59f3ecfc4585"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:b29bfd650ed8e148f9c515474a6ef0ba1090b7a8faeee26b74a8ff3b33617502"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:1e56b9cafcd6531bab5d9b2e890bb4937f4165109fe98e2b98ef0dcfcb06ee9d"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:ec40170327d4a404b0d91855d41bfe1fe4b699222b2b93e3d833a27330a87a6d"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:2df5f139233060578d8c2c975128fb231a89ca0a462b35d4b5fcf7c501ebdbe1"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-win32.whl", hash = "sha256:f973157ffeab5459eefe7b97a804987876dd0a55570b8fa56b4e1954bf11329b"},
+    {file = "aiohttp-3.8.3-cp36-cp36m-win_amd64.whl", hash = "sha256:437399385f2abcd634865705bdc180c8314124b98299d54fe1d4c8990f2f9494"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:09e28f572b21642128ef31f4e8372adb6888846f32fecb288c8b0457597ba61a"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6f3553510abdbec67c043ca85727396ceed1272eef029b050677046d3387be8d"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e168a7560b7c61342ae0412997b069753f27ac4862ec7867eff74f0fe4ea2ad9"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:db4c979b0b3e0fa7e9e69ecd11b2b3174c6963cebadeecfb7ad24532ffcdd11a"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e164e0a98e92d06da343d17d4e9c4da4654f4a4588a20d6c73548a29f176abe2"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e8a78079d9a39ca9ca99a8b0ac2fdc0c4d25fc80c8a8a82e5c8211509c523363"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:21b30885a63c3f4ff5b77a5d6caf008b037cb521a5f33eab445dc566f6d092cc"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:4b0f30372cef3fdc262f33d06e7b411cd59058ce9174ef159ad938c4a34a89da"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:8135fa153a20d82ffb64f70a1b5c2738684afa197839b34cc3e3c72fa88d302c"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:ad61a9639792fd790523ba072c0555cd6be5a0baf03a49a5dd8cfcf20d56df48"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:978b046ca728073070e9abc074b6299ebf3501e8dee5e26efacb13cec2b2dea0"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-win32.whl", hash = "sha256:0d2c6d8c6872df4a6ec37d2ede71eff62395b9e337b4e18efd2177de883a5033"},
+    {file = "aiohttp-3.8.3-cp37-cp37m-win_amd64.whl", hash = "sha256:21d69797eb951f155026651f7e9362877334508d39c2fc37bd04ff55b2007091"},
+    {file = "aiohttp-3.8.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:2ca9af5f8f5812d475c5259393f52d712f6d5f0d7fdad9acdb1107dd9e3cb7eb"},
+    {file = "aiohttp-3.8.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1d90043c1882067f1bd26196d5d2db9aa6d268def3293ed5fb317e13c9413ea4"},
+    {file = "aiohttp-3.8.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:d737fc67b9a970f3234754974531dc9afeea11c70791dcb7db53b0cf81b79784"},
+    {file = "aiohttp-3.8.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ebf909ea0a3fc9596e40d55d8000702a85e27fd578ff41a5500f68f20fd32e6c"},
+    {file = "aiohttp-3.8.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5835f258ca9f7c455493a57ee707b76d2d9634d84d5d7f62e77be984ea80b849"},
+    {file = "aiohttp-3.8.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:da37dcfbf4b7f45d80ee386a5f81122501ec75672f475da34784196690762f4b"},
+    {file = "aiohttp-3.8.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87f44875f2804bc0511a69ce44a9595d5944837a62caecc8490bbdb0e18b1342"},
+    {file = "aiohttp-3.8.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:527b3b87b24844ea7865284aabfab08eb0faf599b385b03c2aa91fc6edd6e4b6"},
+    {file = "aiohttp-3.8.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:d5ba88df9aa5e2f806650fcbeedbe4f6e8736e92fc0e73b0400538fd25a4dd96"},
+    {file = "aiohttp-3.8.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:e7b8813be97cab8cb52b1375f41f8e6804f6507fe4660152e8ca5c48f0436017"},
+    {file = "aiohttp-3.8.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:2dea10edfa1a54098703cb7acaa665c07b4e7568472a47f4e64e6319d3821ccf"},
+    {file = "aiohttp-3.8.3-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:713d22cd9643ba9025d33c4af43943c7a1eb8547729228de18d3e02e278472b6"},
+    {file = "aiohttp-3.8.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2d252771fc85e0cf8da0b823157962d70639e63cb9b578b1dec9868dd1f4f937"},
+    {file = "aiohttp-3.8.3-cp38-cp38-win32.whl", hash = "sha256:66bd5f950344fb2b3dbdd421aaa4e84f4411a1a13fca3aeb2bcbe667f80c9f76"},
+    {file = "aiohttp-3.8.3-cp38-cp38-win_amd64.whl", hash = "sha256:84b14f36e85295fe69c6b9789b51a0903b774046d5f7df538176516c3e422446"},
+    {file = "aiohttp-3.8.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:16c121ba0b1ec2b44b73e3a8a171c4f999b33929cd2397124a8c7fcfc8cd9e06"},
+    {file = "aiohttp-3.8.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8d6aaa4e7155afaf994d7924eb290abbe81a6905b303d8cb61310a2aba1c68ba"},
+    {file = "aiohttp-3.8.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:43046a319664a04b146f81b40e1545d4c8ac7b7dd04c47e40bf09f65f2437346"},
+    {file = "aiohttp-3.8.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:599418aaaf88a6d02a8c515e656f6faf3d10618d3dd95866eb4436520096c84b"},
+    {file = "aiohttp-3.8.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:92a2964319d359f494f16011e23434f6f8ef0434acd3cf154a6b7bec511e2fb7"},
+    {file = "aiohttp-3.8.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:73a4131962e6d91109bca6536416aa067cf6c4efb871975df734f8d2fd821b37"},
+    {file = "aiohttp-3.8.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:598adde339d2cf7d67beaccda3f2ce7c57b3b412702f29c946708f69cf8222aa"},
+    {file = "aiohttp-3.8.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:75880ed07be39beff1881d81e4a907cafb802f306efd6d2d15f2b3c69935f6fb"},
+    {file = "aiohttp-3.8.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:a0239da9fbafd9ff82fd67c16704a7d1bccf0d107a300e790587ad05547681c8"},
+    {file = "aiohttp-3.8.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:4e3a23ec214e95c9fe85a58470b660efe6534b83e6cbe38b3ed52b053d7cb6ad"},
+    {file = "aiohttp-3.8.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:47841407cc89a4b80b0c52276f3cc8138bbbfba4b179ee3acbd7d77ae33f7ac4"},
+    {file = "aiohttp-3.8.3-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:54d107c89a3ebcd13228278d68f1436d3f33f2dd2af5415e3feaeb1156e1a62c"},
+    {file = "aiohttp-3.8.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c37c5cce780349d4d51739ae682dec63573847a2a8dcb44381b174c3d9c8d403"},
+    {file = "aiohttp-3.8.3-cp39-cp39-win32.whl", hash = "sha256:f178d2aadf0166be4df834c4953da2d7eef24719e8aec9a65289483eeea9d618"},
+    {file = "aiohttp-3.8.3-cp39-cp39-win_amd64.whl", hash = "sha256:88e5be56c231981428f4f506c68b6a46fa25c4123a2e86d156c58a8369d31ab7"},
+    {file = "aiohttp-3.8.3.tar.gz", hash = "sha256:3828fb41b7203176b82fe5d699e0d845435f2374750a44b480ea6b930f6be269"},
+]
+
+[package.dependencies]
+aiosignal = ">=1.1.2"
+async-timeout = ">=4.0.0a3,<5.0"
+attrs = ">=17.3.0"
+charset-normalizer = ">=2.0,<3.0"
+frozenlist = ">=1.1.1"
+multidict = ">=4.5,<7.0"
+yarl = ">=1.0,<2.0"
+
+[package.extras]
+speedups = ["Brotli", "aiodns", "cchardet"]
+
+[[package]]
+name = "aiosignal"
+version = "1.3.1"
+description = "aiosignal: a list of registered asynchronous callbacks"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "aiosignal-1.3.1-py3-none-any.whl", hash = "sha256:f8376fb07dd1e86a584e4fcdec80b36b7f81aac666ebc724e2c090300dd83b17"},
+    {file = "aiosignal-1.3.1.tar.gz", hash = "sha256:54cd96e15e1649b75d6c87526a6ff0b6c1b0dd3459f43d9ca11d48c339b68cfc"},
+]
+
+[package.dependencies]
+frozenlist = ">=1.1.0"
+
 [[package]]
 name = "alabaster"
 version = "0.7.13"
@@ -169,7 +293,7 @@ name = "async-timeout"
 version = "4.0.2"
 description = "Timeout context manager for asyncio programs"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 files = [
     {file = "async-timeout-4.0.2.tar.gz", hash = "sha256:2163e1640ddb52b7a8c80d0a67a08587e5d245cc9c553a74a847056bc2976b15"},
@@ -180,7 +304,7 @@ files = [
 name = "attrs"
 version = "22.2.0"
 description = "Classes Without Boilerplate"
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.6"
 files = [
@@ -505,102 +629,19 @@ pycparser = "*"
 
 [[package]]
 name = "charset-normalizer"
-version = "3.0.1"
+version = "2.1.1"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
 category = "main"
 optional = false
-python-versions = "*"
+python-versions = ">=3.6.0"
 files = [
-    {file = "charset-normalizer-3.0.1.tar.gz", hash = "sha256:ebea339af930f8ca5d7a699b921106c6e29c617fe9606fa7baa043c1cdae326f"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:88600c72ef7587fe1708fd242b385b6ed4b8904976d5da0893e31df8b3480cb6"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c75ffc45f25324e68ab238cb4b5c0a38cd1c3d7f1fb1f72b5541de469e2247db"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:db72b07027db150f468fbada4d85b3b2729a3db39178abf5c543b784c1254539"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:62595ab75873d50d57323a91dd03e6966eb79c41fa834b7a1661ed043b2d404d"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ff6f3db31555657f3163b15a6b7c6938d08df7adbfc9dd13d9d19edad678f1e8"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:772b87914ff1152b92a197ef4ea40efe27a378606c39446ded52c8f80f79702e"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70990b9c51340e4044cfc394a81f614f3f90d41397104d226f21e66de668730d"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:292d5e8ba896bbfd6334b096e34bffb56161c81408d6d036a7dfa6929cff8783"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:2edb64ee7bf1ed524a1da60cdcd2e1f6e2b4f66ef7c077680739f1641f62f555"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:31a9ddf4718d10ae04d9b18801bd776693487cbb57d74cc3458a7673f6f34639"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:44ba614de5361b3e5278e1241fda3dc1838deed864b50a10d7ce92983797fa76"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:12db3b2c533c23ab812c2b25934f60383361f8a376ae272665f8e48b88e8e1c6"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c512accbd6ff0270939b9ac214b84fb5ada5f0409c44298361b2f5e13f9aed9e"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-win32.whl", hash = "sha256:502218f52498a36d6bf5ea77081844017bf7982cdbe521ad85e64cabee1b608b"},
-    {file = "charset_normalizer-3.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:601f36512f9e28f029d9481bdaf8e89e5148ac5d89cffd3b05cd533eeb423b59"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0298eafff88c99982a4cf66ba2efa1128e4ddaca0b05eec4c456bbc7db691d8d"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a8d0fc946c784ff7f7c3742310cc8a57c5c6dc31631269876a88b809dbeff3d3"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:87701167f2a5c930b403e9756fab1d31d4d4da52856143b609e30a1ce7160f3c"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14e76c0f23218b8f46c4d87018ca2e441535aed3632ca134b10239dfb6dadd6b"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c0a590235ccd933d9892c627dec5bc7511ce6ad6c1011fdf5b11363022746c1"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8c7fe7afa480e3e82eed58e0ca89f751cd14d767638e2550c77a92a9e749c317"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:79909e27e8e4fcc9db4addea88aa63f6423ebb171db091fb4373e3312cb6d603"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ac7b6a045b814cf0c47f3623d21ebd88b3e8cf216a14790b455ea7ff0135d18"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:72966d1b297c741541ca8cf1223ff262a6febe52481af742036a0b296e35fa5a"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f9d0c5c045a3ca9bedfc35dca8526798eb91a07aa7a2c0fee134c6c6f321cbd7"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:5995f0164fa7df59db4746112fec3f49c461dd6b31b841873443bdb077c13cfc"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4a8fcf28c05c1f6d7e177a9a46a1c52798bfe2ad80681d275b10dcf317deaf0b"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:761e8904c07ad053d285670f36dd94e1b6ab7f16ce62b9805c475b7aa1cffde6"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-win32.whl", hash = "sha256:71140351489970dfe5e60fc621ada3e0f41104a5eddaca47a7acb3c1b851d6d3"},
-    {file = "charset_normalizer-3.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:9ab77acb98eba3fd2a85cd160851816bfce6871d944d885febf012713f06659c"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:84c3990934bae40ea69a82034912ffe5a62c60bbf6ec5bc9691419641d7d5c9a"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74292fc76c905c0ef095fe11e188a32ebd03bc38f3f3e9bcb85e4e6db177b7ea"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c95a03c79bbe30eec3ec2b7f076074f4281526724c8685a42872974ef4d36b72"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f4c39b0e3eac288fedc2b43055cfc2ca7a60362d0e5e87a637beac5d801ef478"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df2c707231459e8a4028eabcd3cfc827befd635b3ef72eada84ab13b52e1574d"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93ad6d87ac18e2a90b0fe89df7c65263b9a99a0eb98f0a3d2e079f12a0735837"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:59e5686dd847347e55dffcc191a96622f016bc0ad89105e24c14e0d6305acbc6"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:cd6056167405314a4dc3c173943f11249fa0f1b204f8b51ed4bde1a9cd1834dc"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:083c8d17153ecb403e5e1eb76a7ef4babfc2c48d58899c98fcaa04833e7a2f9a"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:f5057856d21e7586765171eac8b9fc3f7d44ef39425f85dbcccb13b3ebea806c"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:7eb33a30d75562222b64f569c642ff3dc6689e09adda43a082208397f016c39a"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-win32.whl", hash = "sha256:95dea361dd73757c6f1c0a1480ac499952c16ac83f7f5f4f84f0658a01b8ef41"},
-    {file = "charset_normalizer-3.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:eaa379fcd227ca235d04152ca6704c7cb55564116f8bc52545ff357628e10602"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3e45867f1f2ab0711d60c6c71746ac53537f1684baa699f4f668d4c6f6ce8e14"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cadaeaba78750d58d3cc6ac4d1fd867da6fc73c88156b7a3212a3cd4819d679d"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:911d8a40b2bef5b8bbae2e36a0b103f142ac53557ab421dc16ac4aafee6f53dc"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:503e65837c71b875ecdd733877d852adbc465bd82c768a067badd953bf1bc5a3"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a60332922359f920193b1d4826953c507a877b523b2395ad7bc716ddd386d866"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:16a8663d6e281208d78806dbe14ee9903715361cf81f6d4309944e4d1e59ac5b"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:a16418ecf1329f71df119e8a65f3aa68004a3f9383821edcb20f0702934d8087"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:9d9153257a3f70d5f69edf2325357251ed20f772b12e593f3b3377b5f78e7ef8"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:02a51034802cbf38db3f89c66fb5d2ec57e6fe7ef2f4a44d070a593c3688667b"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:2e396d70bc4ef5325b72b593a72c8979999aa52fb8bcf03f701c1b03e1166918"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:11b53acf2411c3b09e6af37e4b9005cba376c872503c8f28218c7243582df45d"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-win32.whl", hash = "sha256:0bf2dae5291758b6f84cf923bfaa285632816007db0330002fa1de38bfcb7154"},
-    {file = "charset_normalizer-3.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:2c03cc56021a4bd59be889c2b9257dae13bf55041a3372d3295416f86b295fb5"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:024e606be3ed92216e2b6952ed859d86b4cfa52cd5bc5f050e7dc28f9b43ec42"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4b0d02d7102dd0f997580b51edc4cebcf2ab6397a7edf89f1c73b586c614272c"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:358a7c4cb8ba9b46c453b1dd8d9e431452d5249072e4f56cfda3149f6ab1405e"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81d6741ab457d14fdedc215516665050f3822d3e56508921cc7239f8c8e66a58"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8b8af03d2e37866d023ad0ddea594edefc31e827fee64f8de5611a1dbc373174"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9cf4e8ad252f7c38dd1f676b46514f92dc0ebeb0db5552f5f403509705e24753"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e696f0dd336161fca9adbb846875d40752e6eba585843c768935ba5c9960722b"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c22d3fe05ce11d3671297dc8973267daa0f938b93ec716e12e0f6dee81591dc1"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:109487860ef6a328f3eec66f2bf78b0b72400280d8f8ea05f69c51644ba6521a"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:37f8febc8ec50c14f3ec9637505f28e58d4f66752207ea177c1d67df25da5aed"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:f97e83fa6c25693c7a35de154681fcc257c1c41b38beb0304b9c4d2d9e164479"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:a152f5f33d64a6be73f1d30c9cc82dfc73cec6477ec268e7c6e4c7d23c2d2291"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:39049da0ffb96c8cbb65cbf5c5f3ca3168990adf3551bd1dee10c48fce8ae820"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-win32.whl", hash = "sha256:4457ea6774b5611f4bed5eaa5df55f70abde42364d498c5134b7ef4c6958e20e"},
-    {file = "charset_normalizer-3.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:e62164b50f84e20601c1ff8eb55620d2ad25fb81b59e3cd776a1902527a788af"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8eade758719add78ec36dc13201483f8e9b5d940329285edcd5f70c0a9edbd7f"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8499ca8f4502af841f68135133d8258f7b32a53a1d594aa98cc52013fff55678"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3fc1c4a2ffd64890aebdb3f97e1278b0cc72579a08ca4de8cd2c04799a3a22be"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:00d3ffdaafe92a5dc603cb9bd5111aaa36dfa187c8285c543be562e61b755f6b"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c2ac1b08635a8cd4e0cbeaf6f5e922085908d48eb05d44c5ae9eabab148512ca"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f6f45710b4459401609ebebdbcfb34515da4fc2aa886f95107f556ac69a9147e"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ae1de54a77dc0d6d5fcf623290af4266412a7c4be0b1ff7444394f03f5c54e3"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3b590df687e3c5ee0deef9fc8c547d81986d9a1b56073d82de008744452d6541"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ab5de034a886f616a5668aa5d098af2b5385ed70142090e2a31bcbd0af0fdb3d"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9cb3032517f1627cc012dbc80a8ec976ae76d93ea2b5feaa9d2a5b8882597579"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:608862a7bf6957f2333fc54ab4399e405baad0163dc9f8d99cb236816db169d4"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:0f438ae3532723fb6ead77e7c604be7c8374094ef4ee2c5e03a3a17f1fca256c"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:356541bf4381fa35856dafa6a965916e54bed415ad8a24ee6de6e37deccf2786"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-win32.whl", hash = "sha256:39cf9ed17fe3b1bc81f33c9ceb6ce67683ee7526e65fde1447c772afc54a1bb8"},
-    {file = "charset_normalizer-3.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:0a11e971ed097d24c534c037d298ad32c6ce81a45736d31e0ff0ad37ab437d59"},
-    {file = "charset_normalizer-3.0.1-py3-none-any.whl", hash = "sha256:7e189e2e1d3ed2f4aebabd2d5b0f931e883676e51c7624826e0a4e5fe8a0bf24"},
+    {file = "charset-normalizer-2.1.1.tar.gz", hash = "sha256:5a3d016c7c547f69d6f81fb0db9449ce888b418b5b9952cc5e6e66843e9dd845"},
+    {file = "charset_normalizer-2.1.1-py3-none-any.whl", hash = "sha256:83e9a75d1911279afd89352c68b45348559d1fc0506b054b346651b5e7fee29f"},
 ]
 
+[package.extras]
+unicode-backport = ["unicodedata2"]
+
 [[package]]
 name = "click"
 version = "8.1.3"
@@ -1214,6 +1255,90 @@ files = [
 [package.dependencies]
 python-dateutil = ">=2.7"
 
+[[package]]
+name = "frozenlist"
+version = "1.3.3"
+description = "A list-like structure which implements collections.abc.MutableSequence"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "frozenlist-1.3.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ff8bf625fe85e119553b5383ba0fb6aa3d0ec2ae980295aaefa552374926b3f4"},
+    {file = "frozenlist-1.3.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dfbac4c2dfcc082fcf8d942d1e49b6aa0766c19d3358bd86e2000bf0fa4a9cf0"},
+    {file = "frozenlist-1.3.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b1c63e8d377d039ac769cd0926558bb7068a1f7abb0f003e3717ee003ad85530"},
+    {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7fdfc24dcfce5b48109867c13b4cb15e4660e7bd7661741a391f821f23dfdca7"},
+    {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2c926450857408e42f0bbc295e84395722ce74bae69a3b2aa2a65fe22cb14b99"},
+    {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1841e200fdafc3d51f974d9d377c079a0694a8f06de2e67b48150328d66d5483"},
+    {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f470c92737afa7d4c3aacc001e335062d582053d4dbe73cda126f2d7031068dd"},
+    {file = "frozenlist-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:783263a4eaad7c49983fe4b2e7b53fa9770c136c270d2d4bbb6d2192bf4d9caf"},
+    {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:924620eef691990dfb56dc4709f280f40baee568c794b5c1885800c3ecc69816"},
+    {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ae4dc05c465a08a866b7a1baf360747078b362e6a6dbeb0c57f234db0ef88ae0"},
+    {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:bed331fe18f58d844d39ceb398b77d6ac0b010d571cba8267c2e7165806b00ce"},
+    {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:02c9ac843e3390826a265e331105efeab489ffaf4dd86384595ee8ce6d35ae7f"},
+    {file = "frozenlist-1.3.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:9545a33965d0d377b0bc823dcabf26980e77f1b6a7caa368a365a9497fb09420"},
+    {file = "frozenlist-1.3.3-cp310-cp310-win32.whl", hash = "sha256:d5cd3ab21acbdb414bb6c31958d7b06b85eeb40f66463c264a9b343a4e238642"},
+    {file = "frozenlist-1.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:b756072364347cb6aa5b60f9bc18e94b2f79632de3b0190253ad770c5df17db1"},
+    {file = "frozenlist-1.3.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b4395e2f8d83fbe0c627b2b696acce67868793d7d9750e90e39592b3626691b7"},
+    {file = "frozenlist-1.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:14143ae966a6229350021384870458e4777d1eae4c28d1a7aa47f24d030e6678"},
+    {file = "frozenlist-1.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5d8860749e813a6f65bad8285a0520607c9500caa23fea6ee407e63debcdbef6"},
+    {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23d16d9f477bb55b6154654e0e74557040575d9d19fe78a161bd33d7d76808e8"},
+    {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:eb82dbba47a8318e75f679690190c10a5e1f447fbf9df41cbc4c3afd726d88cb"},
+    {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9309869032abb23d196cb4e4db574232abe8b8be1339026f489eeb34a4acfd91"},
+    {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a97b4fe50b5890d36300820abd305694cb865ddb7885049587a5678215782a6b"},
+    {file = "frozenlist-1.3.3-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c188512b43542b1e91cadc3c6c915a82a5eb95929134faf7fd109f14f9892ce4"},
+    {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:303e04d422e9b911a09ad499b0368dc551e8c3cd15293c99160c7f1f07b59a48"},
+    {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:0771aed7f596c7d73444c847a1c16288937ef988dc04fb9f7be4b2aa91db609d"},
+    {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:66080ec69883597e4d026f2f71a231a1ee9887835902dbe6b6467d5a89216cf6"},
+    {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:41fe21dc74ad3a779c3d73a2786bdf622ea81234bdd4faf90b8b03cad0c2c0b4"},
+    {file = "frozenlist-1.3.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f20380df709d91525e4bee04746ba612a4df0972c1b8f8e1e8af997e678c7b81"},
+    {file = "frozenlist-1.3.3-cp311-cp311-win32.whl", hash = "sha256:f30f1928162e189091cf4d9da2eac617bfe78ef907a761614ff577ef4edfb3c8"},
+    {file = "frozenlist-1.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:a6394d7dadd3cfe3f4b3b186e54d5d8504d44f2d58dcc89d693698e8b7132b32"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8df3de3a9ab8325f94f646609a66cbeeede263910c5c0de0101079ad541af332"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0693c609e9742c66ba4870bcee1ad5ff35462d5ffec18710b4ac89337ff16e27"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cd4210baef299717db0a600d7a3cac81d46ef0e007f88c9335db79f8979c0d3d"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:394c9c242113bfb4b9aa36e2b80a05ffa163a30691c7b5a29eba82e937895d5e"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6327eb8e419f7d9c38f333cde41b9ae348bec26d840927332f17e887a8dcb70d"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2e24900aa13212e75e5b366cb9065e78bbf3893d4baab6052d1aca10d46d944c"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:3843f84a6c465a36559161e6c59dce2f2ac10943040c2fd021cfb70d58c4ad56"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:84610c1502b2461255b4c9b7d5e9c48052601a8957cd0aea6ec7a7a1e1fb9420"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:c21b9aa40e08e4f63a2f92ff3748e6b6c84d717d033c7b3438dd3123ee18f70e"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:efce6ae830831ab6a22b9b4091d411698145cb9b8fc869e1397ccf4b4b6455cb"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:40de71985e9042ca00b7953c4f41eabc3dc514a2d1ff534027f091bc74416401"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-win32.whl", hash = "sha256:180c00c66bde6146a860cbb81b54ee0df350d2daf13ca85b275123bbf85de18a"},
+    {file = "frozenlist-1.3.3-cp37-cp37m-win_amd64.whl", hash = "sha256:9bbbcedd75acdfecf2159663b87f1bb5cfc80e7cd99f7ddd9d66eb98b14a8411"},
+    {file = "frozenlist-1.3.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:034a5c08d36649591be1cbb10e09da9f531034acfe29275fc5454a3b101ce41a"},
+    {file = "frozenlist-1.3.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ba64dc2b3b7b158c6660d49cdb1d872d1d0bf4e42043ad8d5006099479a194e5"},
+    {file = "frozenlist-1.3.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:47df36a9fe24054b950bbc2db630d508cca3aa27ed0566c0baf661225e52c18e"},
+    {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:008a054b75d77c995ea26629ab3a0c0d7281341f2fa7e1e85fa6153ae29ae99c"},
+    {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:841ea19b43d438a80b4de62ac6ab21cfe6827bb8a9dc62b896acc88eaf9cecba"},
+    {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e235688f42b36be2b6b06fc37ac2126a73b75fb8d6bc66dd632aa35286238703"},
+    {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ca713d4af15bae6e5d79b15c10c8522859a9a89d3b361a50b817c98c2fb402a2"},
+    {file = "frozenlist-1.3.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ac5995f2b408017b0be26d4a1d7c61bce106ff3d9e3324374d66b5964325448"},
+    {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:a4ae8135b11652b08a8baf07631d3ebfe65a4c87909dbef5fa0cdde440444ee4"},
+    {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:4ea42116ceb6bb16dbb7d526e242cb6747b08b7710d9782aa3d6732bd8d27649"},
+    {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:810860bb4bdce7557bc0febb84bbd88198b9dbc2022d8eebe5b3590b2ad6c842"},
+    {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:ee78feb9d293c323b59a6f2dd441b63339a30edf35abcb51187d2fc26e696d13"},
+    {file = "frozenlist-1.3.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:0af2e7c87d35b38732e810befb9d797a99279cbb85374d42ea61c1e9d23094b3"},
+    {file = "frozenlist-1.3.3-cp38-cp38-win32.whl", hash = "sha256:899c5e1928eec13fd6f6d8dc51be23f0d09c5281e40d9cf4273d188d9feeaf9b"},
+    {file = "frozenlist-1.3.3-cp38-cp38-win_amd64.whl", hash = "sha256:7f44e24fa70f6fbc74aeec3e971f60a14dde85da364aa87f15d1be94ae75aeef"},
+    {file = "frozenlist-1.3.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:2b07ae0c1edaa0a36339ec6cce700f51b14a3fc6545fdd32930d2c83917332cf"},
+    {file = "frozenlist-1.3.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ebb86518203e12e96af765ee89034a1dbb0c3c65052d1b0c19bbbd6af8a145e1"},
+    {file = "frozenlist-1.3.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:5cf820485f1b4c91e0417ea0afd41ce5cf5965011b3c22c400f6d144296ccbc0"},
+    {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c11e43016b9024240212d2a65043b70ed8dfd3b52678a1271972702d990ac6d"},
+    {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8fa3c6e3305aa1146b59a09b32b2e04074945ffcfb2f0931836d103a2c38f936"},
+    {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:352bd4c8c72d508778cf05ab491f6ef36149f4d0cb3c56b1b4302852255d05d5"},
+    {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:65a5e4d3aa679610ac6e3569e865425b23b372277f89b5ef06cf2cdaf1ebf22b"},
+    {file = "frozenlist-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b1e2c1185858d7e10ff045c496bbf90ae752c28b365fef2c09cf0fa309291669"},
+    {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f163d2fd041c630fed01bc48d28c3ed4a3b003c00acd396900e11ee5316b56bb"},
+    {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:05cdb16d09a0832eedf770cb7bd1fe57d8cf4eaf5aced29c4e41e3f20b30a784"},
+    {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:8bae29d60768bfa8fb92244b74502b18fae55a80eac13c88eb0b496d4268fd2d"},
+    {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:eedab4c310c0299961ac285591acd53dc6723a1ebd90a57207c71f6e0c2153ab"},
+    {file = "frozenlist-1.3.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:3bbdf44855ed8f0fbcd102ef05ec3012d6a4fd7c7562403f76ce6a52aeffb2b1"},
+    {file = "frozenlist-1.3.3-cp39-cp39-win32.whl", hash = "sha256:efa568b885bca461f7c7b9e032655c0c143d305bf01c30caf6db2854a4532b38"},
+    {file = "frozenlist-1.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:cfe33efc9cb900a4c46f91a5ceba26d6df370ffddd9ca386eb1d4f0ad97b9ea9"},
+    {file = "frozenlist-1.3.3.tar.gz", hash = "sha256:58bcc55721e8a90b88332d6cd441261ebb22342e238296bb330968952fbb3a6a"},
+]
+
 [[package]]
 name = "gast"
 version = "0.4.0"
@@ -2712,6 +2837,90 @@ files = [
     {file = "more_itertools-9.0.0-py3-none-any.whl", hash = "sha256:250e83d7e81d0c87ca6bd942e6aeab8cc9daa6096d12c5308f3f92fa5e5c1f41"},
 ]
 
+[[package]]
+name = "multidict"
+version = "6.0.4"
+description = "multidict implementation"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b1a97283e0c85772d613878028fec909f003993e1007eafa715b24b377cb9b8"},
+    {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eeb6dcc05e911516ae3d1f207d4b0520d07f54484c49dfc294d6e7d63b734171"},
+    {file = "multidict-6.0.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d6d635d5209b82a3492508cf5b365f3446afb65ae7ebd755e70e18f287b0adf7"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c048099e4c9e9d615545e2001d3d8a4380bd403e1a0578734e0d31703d1b0c0b"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ea20853c6dbbb53ed34cb4d080382169b6f4554d394015f1bef35e881bf83547"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:16d232d4e5396c2efbbf4f6d4df89bfa905eb0d4dc5b3549d872ab898451f569"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36c63aaa167f6c6b04ef2c85704e93af16c11d20de1d133e39de6a0e84582a93"},
+    {file = "multidict-6.0.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:64bdf1086b6043bf519869678f5f2757f473dee970d7abf6da91ec00acb9cb98"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:43644e38f42e3af682690876cff722d301ac585c5b9e1eacc013b7a3f7b696a0"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7582a1d1030e15422262de9f58711774e02fa80df0d1578995c76214f6954988"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:ddff9c4e225a63a5afab9dd15590432c22e8057e1a9a13d28ed128ecf047bbdc"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:ee2a1ece51b9b9e7752e742cfb661d2a29e7bcdba2d27e66e28a99f1890e4fa0"},
+    {file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a2e4369eb3d47d2034032a26c7a80fcb21a2cb22e1173d761a162f11e562caa5"},
+    {file = "multidict-6.0.4-cp310-cp310-win32.whl", hash = "sha256:574b7eae1ab267e5f8285f0fe881f17efe4b98c39a40858247720935b893bba8"},
+    {file = "multidict-6.0.4-cp310-cp310-win_amd64.whl", hash = "sha256:4dcbb0906e38440fa3e325df2359ac6cb043df8e58c965bb45f4e406ecb162cc"},
+    {file = "multidict-6.0.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0dfad7a5a1e39c53ed00d2dd0c2e36aed4650936dc18fd9a1826a5ae1cad6f03"},
+    {file = "multidict-6.0.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:64da238a09d6039e3bd39bb3aee9c21a5e34f28bfa5aa22518581f910ff94af3"},
+    {file = "multidict-6.0.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ff959bee35038c4624250473988b24f846cbeb2c6639de3602c073f10410ceba"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:01a3a55bd90018c9c080fbb0b9f4891db37d148a0a18722b42f94694f8b6d4c9"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5cb09abb18c1ea940fb99360ea0396f34d46566f157122c92dfa069d3e0e982"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:666daae833559deb2d609afa4490b85830ab0dfca811a98b70a205621a6109fe"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11bdf3f5e1518b24530b8241529d2050014c884cf18b6fc69c0c2b30ca248710"},
+    {file = "multidict-6.0.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7d18748f2d30f94f498e852c67d61261c643b349b9d2a581131725595c45ec6c"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:458f37be2d9e4c95e2d8866a851663cbc76e865b78395090786f6cd9b3bbf4f4"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:b1a2eeedcead3a41694130495593a559a668f382eee0727352b9a41e1c45759a"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7d6ae9d593ef8641544d6263c7fa6408cc90370c8cb2bbb65f8d43e5b0351d9c"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:5979b5632c3e3534e42ca6ff856bb24b2e3071b37861c2c727ce220d80eee9ed"},
+    {file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:dcfe792765fab89c365123c81046ad4103fcabbc4f56d1c1997e6715e8015461"},
+    {file = "multidict-6.0.4-cp311-cp311-win32.whl", hash = "sha256:3601a3cece3819534b11d4efc1eb76047488fddd0c85a3948099d5da4d504636"},
+    {file = "multidict-6.0.4-cp311-cp311-win_amd64.whl", hash = "sha256:81a4f0b34bd92df3da93315c6a59034df95866014ac08535fc819f043bfd51f0"},
+    {file = "multidict-6.0.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:67040058f37a2a51ed8ea8f6b0e6ee5bd78ca67f169ce6122f3e2ec80dfe9b78"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:853888594621e6604c978ce2a0444a1e6e70c8d253ab65ba11657659dcc9100f"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:39ff62e7d0f26c248b15e364517a72932a611a9b75f35b45be078d81bdb86603"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:af048912e045a2dc732847d33821a9d84ba553f5c5f028adbd364dd4765092ac"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b1e8b901e607795ec06c9e42530788c45ac21ef3aaa11dbd0c69de543bfb79a9"},
+    {file = "multidict-6.0.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62501642008a8b9871ddfccbf83e4222cf8ac0d5aeedf73da36153ef2ec222d2"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:99b76c052e9f1bc0721f7541e5e8c05db3941eb9ebe7b8553c625ef88d6eefde"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:509eac6cf09c794aa27bcacfd4d62c885cce62bef7b2c3e8b2e49d365b5003fe"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:21a12c4eb6ddc9952c415f24eef97e3e55ba3af61f67c7bc388dcdec1404a067"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:5cad9430ab3e2e4fa4a2ef4450f548768400a2ac635841bc2a56a2052cdbeb87"},
+    {file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ab55edc2e84460694295f401215f4a58597f8f7c9466faec545093045476327d"},
+    {file = "multidict-6.0.4-cp37-cp37m-win32.whl", hash = "sha256:5a4dcf02b908c3b8b17a45fb0f15b695bf117a67b76b7ad18b73cf8e92608775"},
+    {file = "multidict-6.0.4-cp37-cp37m-win_amd64.whl", hash = "sha256:6ed5f161328b7df384d71b07317f4d8656434e34591f20552c7bcef27b0ab88e"},
+    {file = "multidict-6.0.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5fc1b16f586f049820c5c5b17bb4ee7583092fa0d1c4e28b5239181ff9532e0c"},
+    {file = "multidict-6.0.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1502e24330eb681bdaa3eb70d6358e818e8e8f908a22a1851dfd4e15bc2f8161"},
+    {file = "multidict-6.0.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b692f419760c0e65d060959df05f2a531945af31fda0c8a3b3195d4efd06de11"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:45e1ecb0379bfaab5eef059f50115b54571acfbe422a14f668fc8c27ba410e7e"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ddd3915998d93fbcd2566ddf9cf62cdb35c9e093075f862935573d265cf8f65d"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:59d43b61c59d82f2effb39a93c48b845efe23a3852d201ed2d24ba830d0b4cf2"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc8e1d0c705233c5dd0c5e6460fbad7827d5d36f310a0fadfd45cc3029762258"},
+    {file = "multidict-6.0.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d6aa0418fcc838522256761b3415822626f866758ee0bc6632c9486b179d0b52"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6748717bb10339c4760c1e63da040f5f29f5ed6e59d76daee30305894069a660"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:4d1a3d7ef5e96b1c9e92f973e43aa5e5b96c659c9bc3124acbbd81b0b9c8a951"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4372381634485bec7e46718edc71528024fcdc6f835baefe517b34a33c731d60"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:fc35cb4676846ef752816d5be2193a1e8367b4c1397b74a565a9d0389c433a1d"},
+    {file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:4b9d9e4e2b37daddb5c23ea33a3417901fa7c7b3dee2d855f63ee67a0b21e5b1"},
+    {file = "multidict-6.0.4-cp38-cp38-win32.whl", hash = "sha256:e41b7e2b59679edfa309e8db64fdf22399eec4b0b24694e1b2104fb789207779"},
+    {file = "multidict-6.0.4-cp38-cp38-win_amd64.whl", hash = "sha256:d6c254ba6e45d8e72739281ebc46ea5eb5f101234f3ce171f0e9f5cc86991480"},
+    {file = "multidict-6.0.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:16ab77bbeb596e14212e7bab8429f24c1579234a3a462105cda4a66904998664"},
+    {file = "multidict-6.0.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc779e9e6f7fda81b3f9aa58e3a6091d49ad528b11ed19f6621408806204ad35"},
+    {file = "multidict-6.0.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4ceef517eca3e03c1cceb22030a3e39cb399ac86bff4e426d4fc6ae49052cc60"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:281af09f488903fde97923c7744bb001a9b23b039a909460d0f14edc7bf59706"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:52f2dffc8acaba9a2f27174c41c9e57f60b907bb9f096b36b1a1f3be71c6284d"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b41156839806aecb3641f3208c0dafd3ac7775b9c4c422d82ee2a45c34ba81ca"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d5e3fc56f88cc98ef8139255cf8cd63eb2c586531e43310ff859d6bb3a6b51f1"},
+    {file = "multidict-6.0.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8316a77808c501004802f9beebde51c9f857054a0c871bd6da8280e718444449"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f70b98cd94886b49d91170ef23ec5c0e8ebb6f242d734ed7ed677b24d50c82cf"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bf6774e60d67a9efe02b3616fee22441d86fab4c6d335f9d2051d19d90a40063"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:e69924bfcdda39b722ef4d9aa762b2dd38e4632b3641b1d9a57ca9cd18f2f83a"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:6b181d8c23da913d4ff585afd1155a0e1194c0b50c54fcfe286f70cdaf2b7176"},
+    {file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:52509b5be062d9eafc8170e53026fbc54cf3b32759a23d07fd935fb04fc22d95"},
+    {file = "multidict-6.0.4-cp39-cp39-win32.whl", hash = "sha256:27c523fbfbdfd19c6867af7346332b62b586eed663887392cff78d614f9ec313"},
+    {file = "multidict-6.0.4-cp39-cp39-win_amd64.whl", hash = "sha256:33029f5734336aa0d4c0384525da0387ef89148dc7191aae00ca5fb23d7aafc2"},
+    {file = "multidict-6.0.4.tar.gz", hash = "sha256:3666906492efb76453c0e7b97f2cf459b0682e7402c0489a95484965dbc1da49"},
+]
+
 [[package]]
 name = "murmurhash"
 version = "1.0.9"
@@ -3899,6 +4108,25 @@ tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
 [package.extras]
 testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "xmlschema"]
 
+[[package]]
+name = "pytest-asyncio"
+version = "0.20.3"
+description = "Pytest support for asyncio"
+category = "dev"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "pytest-asyncio-0.20.3.tar.gz", hash = "sha256:83cbf01169ce3e8eb71c6c278ccb0574d1a7a3bb8eaaf5e50e0ad342afb33b36"},
+    {file = "pytest_asyncio-0.20.3-py3-none-any.whl", hash = "sha256:f129998b209d04fcc65c96fc85c11e5316738358909a8399e93be553d7656442"},
+]
+
+[package.dependencies]
+pytest = ">=6.1.0"
+
+[package.extras]
+docs = ["sphinx (>=5.3)", "sphinx-rtd-theme (>=1.0)"]
+testing = ["coverage (>=6.2)", "flaky (>=3.5.0)", "hypothesis (>=5.7.1)", "mypy (>=0.931)", "pytest-trio (>=0.7.0)"]
+
 [[package]]
 name = "pytest-cov"
 version = "4.0.0"
@@ -6246,6 +6474,94 @@ files = [
     {file = "xmltodict-0.13.0.tar.gz", hash = "sha256:341595a488e3e01a85a9d8911d8912fd922ede5fecc4dce437eb4b6c8d037e56"},
 ]
 
+[[package]]
+name = "yarl"
+version = "1.8.2"
+description = "Yet another URL library"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "yarl-1.8.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:bb81f753c815f6b8e2ddd2eef3c855cf7da193b82396ac013c661aaa6cc6b0a5"},
+    {file = "yarl-1.8.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:47d49ac96156f0928f002e2424299b2c91d9db73e08c4cd6742923a086f1c863"},
+    {file = "yarl-1.8.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3fc056e35fa6fba63248d93ff6e672c096f95f7836938241ebc8260e062832fe"},
+    {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:58a3c13d1c3005dbbac5c9f0d3210b60220a65a999b1833aa46bd6677c69b08e"},
+    {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:10b08293cda921157f1e7c2790999d903b3fd28cd5c208cf8826b3b508026996"},
+    {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:de986979bbd87272fe557e0a8fcb66fd40ae2ddfe28a8b1ce4eae22681728fef"},
+    {file = "yarl-1.8.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c4fcfa71e2c6a3cb568cf81aadc12768b9995323186a10827beccf5fa23d4f8"},
+    {file = "yarl-1.8.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae4d7ff1049f36accde9e1ef7301912a751e5bae0a9d142459646114c70ecba6"},
+    {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:bf071f797aec5b96abfc735ab97da9fd8f8768b43ce2abd85356a3127909d146"},
+    {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:74dece2bfc60f0f70907c34b857ee98f2c6dd0f75185db133770cd67300d505f"},
+    {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:df60a94d332158b444301c7f569659c926168e4d4aad2cfbf4bce0e8fb8be826"},
+    {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:63243b21c6e28ec2375f932a10ce7eda65139b5b854c0f6b82ed945ba526bff3"},
+    {file = "yarl-1.8.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:cfa2bbca929aa742b5084fd4663dd4b87c191c844326fcb21c3afd2d11497f80"},
+    {file = "yarl-1.8.2-cp310-cp310-win32.whl", hash = "sha256:b05df9ea7496df11b710081bd90ecc3a3db6adb4fee36f6a411e7bc91a18aa42"},
+    {file = "yarl-1.8.2-cp310-cp310-win_amd64.whl", hash = "sha256:24ad1d10c9db1953291f56b5fe76203977f1ed05f82d09ec97acb623a7976574"},
+    {file = "yarl-1.8.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:2a1fca9588f360036242f379bfea2b8b44cae2721859b1c56d033adfd5893634"},
+    {file = "yarl-1.8.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f37db05c6051eff17bc832914fe46869f8849de5b92dc4a3466cd63095d23dfd"},
+    {file = "yarl-1.8.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:77e913b846a6b9c5f767b14dc1e759e5aff05502fe73079f6f4176359d832581"},
+    {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0978f29222e649c351b173da2b9b4665ad1feb8d1daa9d971eb90df08702668a"},
+    {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:388a45dc77198b2460eac0aca1efd6a7c09e976ee768b0d5109173e521a19daf"},
+    {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2305517e332a862ef75be8fad3606ea10108662bc6fe08509d5ca99503ac2aee"},
+    {file = "yarl-1.8.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42430ff511571940d51e75cf42f1e4dbdded477e71c1b7a17f4da76c1da8ea76"},
+    {file = "yarl-1.8.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3150078118f62371375e1e69b13b48288e44f6691c1069340081c3fd12c94d5b"},
+    {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c15163b6125db87c8f53c98baa5e785782078fbd2dbeaa04c6141935eb6dab7a"},
+    {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:4d04acba75c72e6eb90745447d69f84e6c9056390f7a9724605ca9c56b4afcc6"},
+    {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:e7fd20d6576c10306dea2d6a5765f46f0ac5d6f53436217913e952d19237efc4"},
+    {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:75c16b2a900b3536dfc7014905a128a2bea8fb01f9ee26d2d7d8db0a08e7cb2c"},
+    {file = "yarl-1.8.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:6d88056a04860a98341a0cf53e950e3ac9f4e51d1b6f61a53b0609df342cc8b2"},
+    {file = "yarl-1.8.2-cp311-cp311-win32.whl", hash = "sha256:fb742dcdd5eec9f26b61224c23baea46c9055cf16f62475e11b9b15dfd5c117b"},
+    {file = "yarl-1.8.2-cp311-cp311-win_amd64.whl", hash = "sha256:8c46d3d89902c393a1d1e243ac847e0442d0196bbd81aecc94fcebbc2fd5857c"},
+    {file = "yarl-1.8.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:ceff9722e0df2e0a9e8a79c610842004fa54e5b309fe6d218e47cd52f791d7ef"},
+    {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f6b4aca43b602ba0f1459de647af954769919c4714706be36af670a5f44c9c1"},
+    {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1684a9bd9077e922300ecd48003ddae7a7474e0412bea38d4631443a91d61077"},
+    {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ebb78745273e51b9832ef90c0898501006670d6e059f2cdb0e999494eb1450c2"},
+    {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3adeef150d528ded2a8e734ebf9ae2e658f4c49bf413f5f157a470e17a4a2e89"},
+    {file = "yarl-1.8.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:57a7c87927a468e5a1dc60c17caf9597161d66457a34273ab1760219953f7f4c"},
+    {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:efff27bd8cbe1f9bd127e7894942ccc20c857aa8b5a0327874f30201e5ce83d0"},
+    {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:a783cd344113cb88c5ff7ca32f1f16532a6f2142185147822187913eb989f739"},
+    {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:705227dccbe96ab02c7cb2c43e1228e2826e7ead880bb19ec94ef279e9555b5b"},
+    {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:34c09b43bd538bf6c4b891ecce94b6fa4f1f10663a8d4ca589a079a5018f6ed7"},
+    {file = "yarl-1.8.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:a48f4f7fea9a51098b02209d90297ac324241bf37ff6be6d2b0149ab2bd51b37"},
+    {file = "yarl-1.8.2-cp37-cp37m-win32.whl", hash = "sha256:0414fd91ce0b763d4eadb4456795b307a71524dbacd015c657bb2a39db2eab89"},
+    {file = "yarl-1.8.2-cp37-cp37m-win_amd64.whl", hash = "sha256:d881d152ae0007809c2c02e22aa534e702f12071e6b285e90945aa3c376463c5"},
+    {file = "yarl-1.8.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5df5e3d04101c1e5c3b1d69710b0574171cc02fddc4b23d1b2813e75f35a30b1"},
+    {file = "yarl-1.8.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7a66c506ec67eb3159eea5096acd05f5e788ceec7b96087d30c7d2865a243918"},
+    {file = "yarl-1.8.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:2b4fa2606adf392051d990c3b3877d768771adc3faf2e117b9de7eb977741229"},
+    {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e21fb44e1eff06dd6ef971d4bdc611807d6bd3691223d9c01a18cec3677939e"},
+    {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:93202666046d9edadfe9f2e7bf5e0782ea0d497b6d63da322e541665d65a044e"},
+    {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fc77086ce244453e074e445104f0ecb27530d6fd3a46698e33f6c38951d5a0f1"},
+    {file = "yarl-1.8.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64dd68a92cab699a233641f5929a40f02a4ede8c009068ca8aa1fe87b8c20ae3"},
+    {file = "yarl-1.8.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1b372aad2b5f81db66ee7ec085cbad72c4da660d994e8e590c997e9b01e44901"},
+    {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:e6f3515aafe0209dd17fb9bdd3b4e892963370b3de781f53e1746a521fb39fc0"},
+    {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:dfef7350ee369197106805e193d420b75467b6cceac646ea5ed3049fcc950a05"},
+    {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:728be34f70a190566d20aa13dc1f01dc44b6aa74580e10a3fb159691bc76909d"},
+    {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:ff205b58dc2929191f68162633d5e10e8044398d7a45265f90a0f1d51f85f72c"},
+    {file = "yarl-1.8.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:baf211dcad448a87a0d9047dc8282d7de59473ade7d7fdf22150b1d23859f946"},
+    {file = "yarl-1.8.2-cp38-cp38-win32.whl", hash = "sha256:272b4f1599f1b621bf2aabe4e5b54f39a933971f4e7c9aa311d6d7dc06965165"},
+    {file = "yarl-1.8.2-cp38-cp38-win_amd64.whl", hash = "sha256:326dd1d3caf910cd26a26ccbfb84c03b608ba32499b5d6eeb09252c920bcbe4f"},
+    {file = "yarl-1.8.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f8ca8ad414c85bbc50f49c0a106f951613dfa5f948ab69c10ce9b128d368baf8"},
+    {file = "yarl-1.8.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:418857f837347e8aaef682679f41e36c24250097f9e2f315d39bae3a99a34cbf"},
+    {file = "yarl-1.8.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ae0eec05ab49e91a78700761777f284c2df119376e391db42c38ab46fd662b77"},
+    {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:009a028127e0a1755c38b03244c0bea9d5565630db9c4cf9572496e947137a87"},
+    {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3edac5d74bb3209c418805bda77f973117836e1de7c000e9755e572c1f7850d0"},
+    {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:da65c3f263729e47351261351b8679c6429151ef9649bba08ef2528ff2c423b2"},
+    {file = "yarl-1.8.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0ef8fb25e52663a1c85d608f6dd72e19bd390e2ecaf29c17fb08f730226e3a08"},
+    {file = "yarl-1.8.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bcd7bb1e5c45274af9a1dd7494d3c52b2be5e6bd8d7e49c612705fd45420b12d"},
+    {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:44ceac0450e648de86da8e42674f9b7077d763ea80c8ceb9d1c3e41f0f0a9951"},
+    {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:97209cc91189b48e7cfe777237c04af8e7cc51eb369004e061809bcdf4e55220"},
+    {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:48dd18adcf98ea9cd721a25313aef49d70d413a999d7d89df44f469edfb38a06"},
+    {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:e59399dda559688461762800d7fb34d9e8a6a7444fd76ec33220a926c8be1516"},
+    {file = "yarl-1.8.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d617c241c8c3ad5c4e78a08429fa49e4b04bedfc507b34b4d8dceb83b4af3588"},
+    {file = "yarl-1.8.2-cp39-cp39-win32.whl", hash = "sha256:cb6d48d80a41f68de41212f3dfd1a9d9898d7841c8f7ce6696cf2fd9cb57ef83"},
+    {file = "yarl-1.8.2-cp39-cp39-win_amd64.whl", hash = "sha256:6604711362f2dbf7160df21c416f81fac0de6dbcf0b5445a2ef25478ecc4c778"},
+    {file = "yarl-1.8.2.tar.gz", hash = "sha256:49d43402c6e3013ad0978602bf6bf5328535c48d192304b91b97a3c6790b1562"},
+]
+
+[package.dependencies]
+idna = ">=2.0"
+multidict = ">=4.0"
+
 [[package]]
 name = "zipp"
 version = "3.12.0"
@@ -6269,4 +6585,4 @@ llms = ["manifest-ml", "torch", "transformers"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "6066217c63ce7620ee615d5db269327e288991f48304526767c88a1870f0c7a0"
+content-hash = "d39158bd758a0665d7a214297ef3b30efee553aaf9f50160d79cd405853d0450"

pyproject.toml

@@ -37,6 +37,7 @@ qdrant-client = {version = "^0.11.7", optional = true}
 dataclasses-json = "^0.5.7"
 tensorflow-text = {version = "^2.11.0", optional = true, python = "^3.10, <3.12"}
 tenacity = "^8.1.0"
+aiohttp = "^3.8.3"
 
 [tool.poetry.group.docs.dependencies]
 autodoc_pydantic = "^1.8.0"
@@ -60,6 +61,7 @@ duckdb-engine = "^0.6.6"
 pytest-watcher = "^0.2.6"
 freezegun = "^1.2.2"
 responses = "^0.22.0"
+pytest-asyncio = "^0.20.3"
 
 [tool.poetry.group.lint.dependencies]
 flake8-docstrings = "^1.6.0"

tests/integration_tests/llms/test_openai.py

@@ -7,6 +7,7 @@ import pytest
 
 from langchain.llms.loading import load_llm
 from langchain.llms.openai import OpenAI
+from langchain.schema import LLMResult
 
 
 def test_openai_call() -> None:
@@ -74,3 +75,11 @@ def test_openai_streaming_error() -> None:
     llm = OpenAI(best_of=2)
     with pytest.raises(ValueError):
         llm.stream("I'm Pickle Rick")
+
+
+@pytest.mark.asyncio
+async def test_openai_async_generate() -> None:
+    """Test async generation."""
+    llm = OpenAI(max_tokens=10)
+    output = await llm.agenerate(["Hello, how are you?"])
+    assert isinstance(output, LLMResult)

tests/unit_tests/chains/test_hyde.py

@@ -33,6 +33,11 @@ class FakeLLM(BaseLLM, BaseModel):
     ) -> LLMResult:
         return LLMResult(generations=[[Generation(text="foo") for _ in range(self.n)]])
 
+    async def _agenerate(
+        self, prompts: List[str], stop: Optional[List[str]] = None
+    ) -> LLMResult:
+        return LLMResult(generations=[[Generation(text="foo") for _ in range(self.n)]])
+
     @property
     def _llm_type(self) -> str:
         """Return type of llm."""