Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-10-31 15:20:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
8b08687fc4
langchain/docs/extras/modules/agents/how_to/async_agent.ipynb

313 lines
20 KiB
Plaintext
Raw Normal View History

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)
2023-02-08 05:21:57 +00:00
{
"cells": [
{
"cell_type": "markdown",
"id": "6fb92deb-d89e-439b-855d-c7f2607d794b",
"metadata": {},
"source": [
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"# Async API\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"LangChain provides async support for Agents by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Async methods are currently supported for the following `Tools`: [`GoogleSerperAPIWrapper`](https://github.com/hwchase17/langchain/blob/master/langchain/utilities/google_serper.py), [`SerpAPIWrapper`](https://github.com/hwchase17/langchain/blob/master/langchain/serpapi.py), [`LLMMathChain`](https://github.com/hwchase17/langchain/blob/master/langchain/chains/llm_math/base.py) and [`Qdrant`](https://github.com/hwchase17/langchain/blob/master/langchain/vectorstores/qdrant.py). Async support for other agent tools are on the roadmap.\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"For `Tool`s that have a `coroutine` implemented (the four 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",
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)
2023-02-08 05:21:57 +00:00
"\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"execution_count": 5,
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)
2023-02-08 05:21:57 +00:00
"id": "da5df06c-af6f-4572-b9f5-0ab971c16487",
"metadata": {
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"ExecuteTime": {
"end_time": "2023-05-04T01:27:22.755025Z",
"start_time": "2023-05-04T01:27:22.754041Z"
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
},
"tags": []
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)
2023-02-08 05:21:57 +00:00
},
"outputs": [],
"source": [
"import asyncio\n",
"import time\n",
"\n",
"from langchain.agents import initialize_agent, load_tools\n",
bump version to 131 (#2391)
2023-04-04 14:21:50 +00:00
"from langchain.agents import AgentType\n",
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)
2023-02-08 05:21:57 +00:00
"from langchain.llms import OpenAI\n",
"from langchain.callbacks.stdout import StdOutCallbackHandler\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",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
" \"Who is Beyonce's husband? What is his age raised to the 0.19 power?\",\n",
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)
2023-02-08 05:21:57 +00:00
"]"
]
},
{
"cell_type": "code",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"execution_count": 3,
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)
2023-02-08 05:21:57 +00:00
"id": "fd4c294e-b1d6-44b8-b32e-2765c017e503",
"metadata": {
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"ExecuteTime": {
"end_time": "2023-05-04T01:15:35.466212Z",
"start_time": "2023-05-04T01:14:05.452245Z"
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
},
"tags": []
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)
2023-02-08 05:21:57 +00:00
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Who won the US Open men's final in 2019?\"\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mRafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ... Draw: 128 (16 Q / 8 WC). Champion: Rafael Nadal. Runner-up: Daniil Medvedev. Score: 7–5, 6–3, 5–7, 4–6, 6–4. Bianca Andreescu won the women's singles title, defeating Serena Williams in straight sets in the final, becoming the first Canadian to win a Grand Slam singles ... Rafael Nadal won his 19th career Grand Slam title, and his fourth US Open crown, by surviving an all-time comback effort from Daniil ... Rafael Nadal beats Daniil Medvedev in US Open final to claim 19th major title. World No2 claims 7-5, 6-3, 5-7, 4-6, 6-4 victory over Russian ... Rafael Nadal defeated Daniil Medvedev in the men's singles final of the U.S. Open on Sunday. Rafael Nadal survived. The 33-year-old defeated Daniil Medvedev in the final of the 2019 U.S. Open to earn his 19th Grand Slam title Sunday ... NEW YORK -- Rafael Nadal defeated Daniil Medvedev in an epic five-set match, 7-5, 6-3, 5-7, 4-6, 6-4 to win the men's singles title at the ... Nadal previously won the U.S. Open three times, most recently in 2017. Ahead of the match, Nadal said he was “super happy to be back in the ... Watch the full match between Daniil Medvedev and Rafael ... Duration: 4:47:32. Posted: Mar 20, 2020. US Open 2019: Rafael Nadal beats Daniil Medvedev · Updated: Sep. 08, 2019, 11:11 p.m. |; Published: Sep · Published: Sep. 08, 2019, 10:06 p.m.. 26. US Open ...\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I now know that Rafael Nadal won the US Open men's final in 2019 and he is 33 years old.\n",
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)
2023-02-08 05:21:57 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 33^0.334\u001B[0m\n",
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 3.215019829667466\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
"Final Answer: Rafael Nadal won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.215019829667466.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Olivia Wilde boyfriend\"\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mSudeikis and Wilde's relationship ended in November 2020. Wilde was publicly served with court documents regarding child custody while she was presenting Don't Worry Darling at CinemaCon 2022. In January 2021, Wilde began dating singer Harry Styles after meeting during the filming of Don't Worry Darling.\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I need to find out Harry Styles' age.\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Harry Styles age\"\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3m29 years\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I need to calculate 29 raised to the 0.23 power.\n",
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)
2023-02-08 05:21:57 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 29^0.23\u001B[0m\n",
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.169459462491557\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
"Final Answer: Harry Styles is Olivia Wilde's boyfriend and his current age raised to the 0.23 power is 2.169459462491557.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m I need to find out who won the most recent grand prix and then calculate their age raised to the 0.23 power.\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"who won the most recent formula 1 grand prix\"\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mMax Verstappen won his first Formula 1 world title on Sunday after the championship was decided by a last-lap overtake of his rival Lewis Hamilton in the Abu Dhabi Grand Prix. Dec 12, 2021\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I need to find out Max Verstappen's age\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Max Verstappen age\"\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3m25 years\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I need to calculate 25 raised to the 0.23 power\n",
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)
2023-02-08 05:21:57 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 25^0.23\u001B[0m\n",
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.096651272316035\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
"Final Answer: Max Verstappen, aged 25, won the most recent Formula 1 grand prix and his age raised to the 0.23 power is 2.096651272316035.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"US Open women's final 2019 winner\"\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mWHAT HAPPENED: #SheTheNorth? She the champion. Nineteen-year-old Canadian Bianca Andreescu sealed her first Grand Slam title on Saturday, downing 23-time major champion Serena Williams in the 2019 US Open women's singles final, 6-3, 7-5. Sep 7, 2019\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I now need to calculate her age raised to the 0.34 power.\n",
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)
2023-02-08 05:21:57 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 19^0.34\u001B[0m\n",
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.7212987634680084\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
"Final Answer: Nineteen-year-old Canadian Bianca Andreescu won the US Open women's final in 2019 and her age raised to the 0.34 power is 2.7212987634680084.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Who is Beyonce's husband?\"\u001B[0m\n",
"Observation: \u001B[36;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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"How old is Jay-Z?\"\u001B[0m\n",
"Observation: \u001B[36;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",
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)
2023-02-08 05:21:57 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 53^0.19\u001B[0m\n",
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.12624064206896\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",
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)
2023-02-08 05:21:57 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Serial executed in 89.97 seconds.\n"
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)
2023-02-08 05:21:57 +00:00
]
}
],
"source": [
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"llm = OpenAI(temperature=0)\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"tools = load_tools([\"google-serper\", \"llm-math\"], llm=llm)\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"s = time.perf_counter()\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"for q in questions:\n",
" agent.run(q)\n",
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)
2023-02-08 05:21:57 +00:00
"elapsed = time.perf_counter() - s\n",
"print(f\"Serial executed in {elapsed:0.2f} seconds.\")"
]
},
{
"cell_type": "code",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"execution_count": 4,
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)
2023-02-08 05:21:57 +00:00
"id": "076d7b85-45ec-465d-8b31-c2ad119c3438",
"metadata": {
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"ExecuteTime": {
"end_time": "2023-05-04T01:26:59.737657Z",
"start_time": "2023-05-04T01:26:42.182078Z"
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
},
"tags": []
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)
2023-02-08 05:21:57 +00:00
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Olivia Wilde boyfriend\"\u001B[0m\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Who is Beyonce's husband?\"\u001B[0m\u001B[32;1m\u001B[1;3m I need to find out who won the most recent formula 1 grand prix and then calculate their age raised to the 0.23 power.\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"most recent formula 1 grand prix winner\"\u001B[0m\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Who won the US Open men's final in 2019?\"\u001B[0m\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",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"US Open women's final 2019 winner\"\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mSudeikis and Wilde's relationship ended in November 2020. Wilde was publicly served with court documents regarding child custody while she was presenting Don't Worry Darling at CinemaCon 2022. In January 2021, Wilde began dating singer Harry Styles after meeting during the filming of Don't Worry Darling.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[36;1m\u001B[1;3mJay-Z\u001B[0m\n",
Make Tools own model, add ToolKit Concept (#1095) Follow-up of @hinthornw's PR: - Migrate the Tool abstraction to a separate file (`BaseTool`). - `Tool` implementation of `BaseTool` takes in function and coroutine to more easily maintain backwards compatibility - Add a Toolkit abstraction that can own the generation of tools around a shared concept or state --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net> Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2023-02-18 21:40:43 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[36;1m\u001B[1;3mRafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ... Draw: 128 (16 Q / 8 WC). Champion: Rafael Nadal. Runner-up: Daniil Medvedev. Score: 7–5, 6–3, 5–7, 4–6, 6–4. Bianca Andreescu won the women's singles title, defeating Serena Williams in straight sets in the final, becoming the first Canadian to win a Grand Slam singles ... Rafael Nadal won his 19th career Grand Slam title, and his fourth US Open crown, by surviving an all-time comback effort from Daniil ... Rafael Nadal beats Daniil Medvedev in US Open final to claim 19th major title. World No2 claims 7-5, 6-3, 5-7, 4-6, 6-4 victory over Russian ... Rafael Nadal defeated Daniil Medvedev in the men's singles final of the U.S. Open on Sunday. Rafael Nadal survived. The 33-year-old defeated Daniil Medvedev in the final of the 2019 U.S. Open to earn his 19th Grand Slam title Sunday ... NEW YORK -- Rafael Nadal defeated Daniil Medvedev in an epic five-set match, 7-5, 6-3, 5-7, 4-6, 6-4 to win the men's singles title at the ... Nadal previously won the U.S. Open three times, most recently in 2017. Ahead of the match, Nadal said he was “super happy to be back in the ... Watch the full match between Daniil Medvedev and Rafael ... Duration: 4:47:32. Posted: Mar 20, 2020. US Open 2019: Rafael Nadal beats Daniil Medvedev · Updated: Sep. 08, 2019, 11:11 p.m. |; Published: Sep · Published: Sep. 08, 2019, 10:06 p.m.. 26. US Open ...\u001B[0m\n",
Make Tools own model, add ToolKit Concept (#1095) Follow-up of @hinthornw's PR: - Migrate the Tool abstraction to a separate file (`BaseTool`). - `Tool` implementation of `BaseTool` takes in function and coroutine to more easily maintain backwards compatibility - Add a Toolkit abstraction that can own the generation of tools around a shared concept or state --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net> Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2023-02-18 21:40:43 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[36;1m\u001B[1;3mWHAT HAPPENED: #SheTheNorth? She the champion. Nineteen-year-old Canadian Bianca Andreescu sealed her first Grand Slam title on Saturday, downing 23-time major champion Serena Williams in the 2019 US Open women's singles final, 6-3, 7-5. Sep 7, 2019\u001B[0m\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[36;1m\u001B[1;3mLewis Hamilton holds the record for the most race wins in Formula One history, with 103 wins to date. Michael Schumacher, the previous record holder, ... Michael Schumacher (top left) and Lewis Hamilton (top right) have each won the championship a record seven times during their careers, while Sebastian Vettel ( ... Grand Prix, Date, Winner, Car, Laps, Time. Bahrain, 05 Mar 2023, Max Verstappen VER, Red Bull Racing Honda RBPT, 57, 1:33:56.736. Saudi Arabia, 19 Mar 2023 ... The Red Bull driver Max Verstappen of the Netherlands celebrated winning his first Formula 1 world title at the Abu Dhabi Grand Prix. Perez wins sprint as Verstappen, Russell clash. Red Bull's Sergio Perez won the first sprint of the 2023 Formula One season after catching and passing Charles ... The most successful driver in the history of F1 is Lewis Hamilton. The man from Stevenage has won 103 Grands Prix throughout his illustrious career and is still ... Lewis Hamilton: 103. Max Verstappen: 37. Michael Schumacher: 91. Fernando Alonso: 32. Max Verstappen and Sergio Perez will race in a very different-looking Red Bull this weekend after the team unveiled a striking special livery for the Miami GP. Lewis Hamilton holds the record of most victories with 103, ahead of Michael Schumacher (91) and Sebastian Vettel (53). Schumacher also holds the record for the ... Lewis Hamilton holds the record for the most race wins in Formula One history, with 103 wins to date. Michael Schumacher, the previous record holder, is second ...\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I need to find out Harry Styles' age.\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"Harry Styles age\"\u001B[0m\u001B[32;1m\u001B[1;3m I need to find out Jay-Z's age\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Google Serper\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: \"How old is Jay-Z?\"\u001B[0m\u001B[32;1m\u001B[1;3m I now know that Rafael Nadal won the US Open men's final in 2019 and he is 33 years old.\n",
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)
2023-02-08 05:21:57 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 33^0.334\u001B[0m\u001B[32;1m\u001B[1;3m I now need to calculate her age raised to the 0.34 power.\n",
Make Tools own model, add ToolKit Concept (#1095) Follow-up of @hinthornw's PR: - Migrate the Tool abstraction to a separate file (`BaseTool`). - `Tool` implementation of `BaseTool` takes in function and coroutine to more easily maintain backwards compatibility - Add a Toolkit abstraction that can own the generation of tools around a shared concept or state --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net> Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2023-02-18 21:40:43 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 19^0.34\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3m29 years\u001B[0m\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[36;1m\u001B[1;3m53 years\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m Max Verstappen won the most recent Formula 1 grand prix.\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: Max Verstappen's age (23) raised to the 0.23 power\u001B[0m\n",
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.7212987634680084\u001B[0m\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 3.215019829667466\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m I need to calculate 29 raised to the 0.23 power.\n",
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)
2023-02-08 05:21:57 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 29^0.23\u001B[0m\u001B[32;1m\u001B[1;3m I need to calculate 53 raised to the 0.19 power\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"Action: Calculator\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Action Input: 53^0.19\u001B[0m\n",
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.0568252837687546\u001B[0m\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.169459462491557\u001B[0m\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
Make Tools own model, add ToolKit Concept (#1095) Follow-up of @hinthornw's PR: - Migrate the Tool abstraction to a separate file (`BaseTool`). - `Tool` implementation of `BaseTool` takes in function and coroutine to more easily maintain backwards compatibility - Add a Toolkit abstraction that can own the generation of tools around a shared concept or state --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net> Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2023-02-18 21:40:43 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
Make Tools own model, add ToolKit Concept (#1095) Follow-up of @hinthornw's PR: - Migrate the Tool abstraction to a separate file (`BaseTool`). - `Tool` implementation of `BaseTool` takes in function and coroutine to more easily maintain backwards compatibility - Add a Toolkit abstraction that can own the generation of tools around a shared concept or state --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net> Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>
2023-02-18 21:40:43 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"Observation: \u001B[33;1m\u001B[1;3mAnswer: 2.12624064206896\u001B[0m\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"Thought:\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
Add async Qdrant to async_agent.ipynb (#7993) I added Qdrant to the async API docs. This is the only vector store that supports full async API. @baskaryan @rlancemartin, @eyurtsev
2023-07-20 13:23:15 +00:00
"\u001B[1m> Finished chain.\u001B[0m\n",
google-serper: async + full json results + support for Google Images, Places and News (#4078) * implemented arun, results, and aresults. Reuses aiosession if available. * helper tools GoogleSerperRun and GoogleSerperResults * support for Google Images, Places and News (examples given) and filtering based on time (e.g. past hour) * updated docs
2023-05-04 05:35:48 +00:00
"Concurrent executed in 17.52 seconds.\n"
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)
2023-02-08 05:21:57 +00:00
]
}
],
"source": [
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"llm = OpenAI(temperature=0)\n",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"tools = load_tools([\"google-serper\", \"llm-math\"], llm=llm)\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")\n",
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)
2023-02-08 05:21:57 +00:00
"\n",
"s = time.perf_counter()\n",
Callbacks Refactor [base] (#3256) Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com> Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-04-30 18:14:09 +00:00
"# If running this outside of Jupyter, use asyncio.run or loop.run_until_complete\n",
"tasks = [agent.arun(q) for q in questions]\n",
"await asyncio.gather(*tasks)\n",
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)
2023-02-08 05:21:57 +00:00
"elapsed = time.perf_counter() - s\n",
"print(f\"Concurrent executed in {elapsed:0.2f} seconds.\")"
]
}
],
"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",
Doc refactor (#6300) Co-authored-by: jacoblee93 <jacoblee93@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 18:52:56 +00:00
"version": "3.11.3"
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)
2023-02-08 05:21:57 +00:00
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink