mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
add chat agent (#1509)
This commit is contained in:
Harrison Chase
GitHub
parent
99fe023496
commit
a094c49153
252
docs/modules/agents/implementations/mrkl_chat.ipynb
Normal file
252
docs/modules/agents/implementations/mrkl_chat.ipynb
Normal file
@ -0,0 +1,252 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f1390152",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# MRKL Chat\n",
|
||||
"\n",
|
||||
"This notebook showcases using an agent to replicate the MRKL chain using an agent optimized for chat models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "39ea3638",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This uses the example Chinook database.\n",
|
||||
"To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ac561cc4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import OpenAI, LLMMathChain, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain\n",
|
||||
"from langchain.agents import initialize_agent, Tool\n",
|
||||
"from langchain.chat_models import ChatOpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "07e96d99",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = ChatOpenAI(temperature=0)\n",
|
||||
"llm1 = OpenAI(temperature=0)\n",
|
||||
"search = SerpAPIWrapper()\n",
|
||||
"llm_math_chain = LLMMathChain(llm=llm1, verbose=True)\n",
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
|
||||
"db_chain = SQLDatabaseChain(llm=llm1, database=db, verbose=True)\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events. You should ask targeted questions\"\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"Calculator\",\n",
|
||||
" func=llm_math_chain.run,\n",
|
||||
" description=\"useful for when you need to answer questions about math\"\n",
|
||||
" ),\n",
|
||||
" Tool(\n",
|
||||
" name=\"FooBar DB\",\n",
|
||||
" func=db_chain.run,\n",
|
||||
" description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\"\n",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "a069c4b6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"mrkl = initialize_agent(tools, llm, agent=\"chat-zero-shot-react-description\", verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e603cd7d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to use the search tool to find out who is Leo DiCaprio's girlfriend and then use the calculator tool to raise her current age to the 0.43 power.\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"Search\",\n",
|
||||
" \"action_input\": \"Who is Leo DiCaprio's girlfriend?\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mCamila Morrone\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mNow I need to use the calculator tool to raise Camila Morrone's current age to the 0.43 power.\n",
|
||||
"Action:\n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"Calculator\",\n",
|
||||
" \"action_input\": \"22.5^(0.43)\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
|
||||
"22.5^(0.43)\u001b[32;1m\u001b[1;3m\n",
|
||||
"```python\n",
|
||||
"import math\n",
|
||||
"print(math.pow(22.5, 0.43))\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"Answer: \u001b[33;1m\u001b[1;3m3.8145075848063126\n",
|
||||
"\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.8145075848063126\n",
|
||||
"\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the final answer\n",
|
||||
"Final Answer: 3.8145075848063126\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'3.8145075848063126'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"mrkl.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "a5c07010",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mThought: I need to use the Search tool to find the name of the artist who recently released an album called 'The Storm Before the Calm'. Then, I can use the FooBar DB tool to check if they are in the database and what albums of theirs are in it.\n",
|
||||
"Action: \n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"Search\",\n",
|
||||
" \"action_input\": \"Who is the artist that recently released an album called 'The Storm Before the Calm'?\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mstudio album by Canadian-American singer-songwriter Alanis Morissette, released June 17, 2022, via Epiphany Music and Thirty Tigers, as well as by RCA Records ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mNow that I know the artist is Alanis Morissette, I can use the FooBar DB tool to check if she is in the database and what albums of hers are in it.\n",
|
||||
"Action: \n",
|
||||
"```\n",
|
||||
"{\n",
|
||||
" \"action\": \"FooBar DB\",\n",
|
||||
" \"action_input\": \"What albums by Alanis Morissette are in the database?\"\n",
|
||||
"}\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
|
||||
"What albums by Alanis Morissette are in the database? \n",
|
||||
"SQLQuery:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/harrisonchase/workplace/langchain/langchain/sql_database.py:141: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
|
||||
" sample_rows = connection.execute(command)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[32;1m\u001b[1;3m SELECT Title FROM Album WHERE ArtistId IN (SELECT ArtistId FROM Artist WHERE Name = 'Alanis Morissette') LIMIT 5;\u001b[0m\n",
|
||||
"SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
|
||||
"Answer:\u001b[32;1m\u001b[1;3m The albums by Alanis Morissette in the database are Jagged Little Pill.\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"Observation: \u001b[38;5;200m\u001b[1;3m The albums by Alanis Morissette in the database are Jagged Little Pill.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mThe only album by Alanis Morissette in the FooBar DB is Jagged Little Pill.\n",
|
||||
"Final Answer: The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The only album of hers in the FooBar DB is Jagged Little Pill.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The only album of hers in the FooBar DB is Jagged Little Pill.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"mrkl.run(\"What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "af016a70",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
0
langchain/agents/chat/__init__.py
Normal file
0
langchain/agents/chat/__init__.py
Normal file
108
langchain/agents/chat/base.py
Normal file
108
langchain/agents/chat/base.py
Normal file
@ -0,0 +1,108 @@
|
||||
import json
|
||||
from typing import Any, List, Optional, Sequence, Tuple
|
||||
|
||||
from langchain.agents.agent import Agent
|
||||
from langchain.agents.chat.prompt import FORMAT_INSTRUCTIONS, PREFIX, SUFFIX
|
||||
from langchain.callbacks.base import BaseCallbackManager
|
||||
from langchain.chains.llm import LLMChain
|
||||
from langchain.prompts.base import BasePromptTemplate
|
||||
from langchain.prompts.chat import (
|
||||
ChatPromptTemplate,
|
||||
HumanMessagePromptTemplate,
|
||||
SystemMessagePromptTemplate,
|
||||
)
|
||||
from langchain.schema import AgentAction, BaseLanguageModel
|
||||
from langchain.tools import BaseTool
|
||||
|
||||
FINAL_ANSWER_ACTION = "Final Answer:"
|
||||
|
||||
|
||||
class ChatAgent(Agent):
|
||||
@property
|
||||
def observation_prefix(self) -> str:
|
||||
"""Prefix to append the observation with."""
|
||||
return "Observation: "
|
||||
|
||||
@property
|
||||
def llm_prefix(self) -> str:
|
||||
"""Prefix to append the llm call with."""
|
||||
return "Thought:"
|
||||
|
||||
def _construct_scratchpad(
|
||||
self, intermediate_steps: List[Tuple[AgentAction, str]]
|
||||
) -> str:
|
||||
agent_scratchpad = super()._construct_scratchpad(intermediate_steps)
|
||||
if agent_scratchpad:
|
||||
return (
|
||||
f"This was your previous work "
|
||||
f"(but I haven't seen any of it! I only see what "
|
||||
f"you return as final answer):\n{agent_scratchpad}"
|
||||
)
|
||||
else:
|
||||
return agent_scratchpad
|
||||
|
||||
def _extract_tool_and_input(self, text: str) -> Optional[Tuple[str, str]]:
|
||||
if FINAL_ANSWER_ACTION in text:
|
||||
return "Final Answer", text.split(FINAL_ANSWER_ACTION)[-1].strip()
|
||||
_, action, _ = text.split("```")
|
||||
|
||||
response = json.loads(action.strip())
|
||||
return response["action"], response["action_input"]
|
||||
|
||||
@property
|
||||
def _stop(self) -> List[str]:
|
||||
return ["Observation:"]
|
||||
|
||||
@classmethod
|
||||
def create_prompt(
|
||||
cls,
|
||||
tools: Sequence[BaseTool],
|
||||
prefix: str = PREFIX,
|
||||
suffix: str = SUFFIX,
|
||||
format_instructions: str = FORMAT_INSTRUCTIONS,
|
||||
input_variables: Optional[List[str]] = None,
|
||||
) -> BasePromptTemplate:
|
||||
tool_strings = "\n".join([f"{tool.name}: {tool.description}" for tool in tools])
|
||||
tool_names = ", ".join([tool.name for tool in tools])
|
||||
format_instructions = format_instructions.format(tool_names=tool_names)
|
||||
template = "\n\n".join([prefix, tool_strings, format_instructions, suffix])
|
||||
messages = [
|
||||
SystemMessagePromptTemplate.from_template(template),
|
||||
HumanMessagePromptTemplate.from_template("{input}\n\n{agent_scratchpad}"),
|
||||
]
|
||||
return ChatPromptTemplate(
|
||||
input_variables=["input", "agent_scratchpad"], messages=messages
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_llm_and_tools(
|
||||
cls,
|
||||
llm: BaseLanguageModel,
|
||||
tools: Sequence[BaseTool],
|
||||
callback_manager: Optional[BaseCallbackManager] = None,
|
||||
prefix: str = PREFIX,
|
||||
suffix: str = SUFFIX,
|
||||
format_instructions: str = FORMAT_INSTRUCTIONS,
|
||||
input_variables: Optional[List[str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> Agent:
|
||||
"""Construct an agent from an LLM and tools."""
|
||||
cls._validate_tools(tools)
|
||||
prompt = cls.create_prompt(
|
||||
tools,
|
||||
prefix=prefix,
|
||||
suffix=suffix,
|
||||
format_instructions=format_instructions,
|
||||
input_variables=input_variables,
|
||||
)
|
||||
llm_chain = LLMChain(
|
||||
llm=llm,
|
||||
prompt=prompt,
|
||||
callback_manager=callback_manager,
|
||||
)
|
||||
tool_names = [tool.name for tool in tools]
|
||||
return cls(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
|
||||
|
||||
@property
|
||||
def _agent_type(self) -> str:
|
||||
raise ValueError
|
||||
27
langchain/agents/chat/prompt.py
Normal file
27
langchain/agents/chat/prompt.py
Normal file
@ -0,0 +1,27 @@
|
||||
# flake8: noqa
|
||||
PREFIX = """Answer the following questions as best you can. You have access to the following tools:"""
|
||||
FORMAT_INSTRUCTIONS = """The way you use the tools is by specifying a json blob.
|
||||
Specifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).
|
||||
|
||||
The $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:
|
||||
|
||||
```
|
||||
{{
|
||||
"action": "calculator",
|
||||
"action_input": "1 + 2"
|
||||
}}
|
||||
```
|
||||
|
||||
ALWAYS use the following format:
|
||||
|
||||
Question: the input question you must answer
|
||||
Thought: you should always think about what to do
|
||||
Action:
|
||||
```
|
||||
$JSON_BLOB
|
||||
```
|
||||
Observation: the result of the action
|
||||
... (this Thought/Action/Observation can repeat N times)
|
||||
Thought: I now know the final answer
|
||||
Final Answer: the final answer to the original input question"""
|
||||
SUFFIX = """Begin! Reminder to always use the exact characters `Final Answer` when responding."""
|
||||
@ -6,6 +6,7 @@ from typing import Any, List, Optional, Union
|
||||
import yaml
|
||||
|
||||
from langchain.agents.agent import Agent
|
||||
from langchain.agents.chat.base import ChatAgent
|
||||
from langchain.agents.conversational.base import ConversationalAgent
|
||||
from langchain.agents.mrkl.base import ZeroShotAgent
|
||||
from langchain.agents.react.base import ReActDocstoreAgent
|
||||
@ -20,6 +21,7 @@ AGENT_TO_CLASS = {
|
||||
"react-docstore": ReActDocstoreAgent,
|
||||
"self-ask-with-search": SelfAskWithSearchAgent,
|
||||
"conversational-react-description": ConversationalAgent,
|
||||
"chat-zero-shot-react-description": ChatAgent,
|
||||
}
|
||||
|
||||
URL_BASE = "https://raw.githubusercontent.com/hwchase17/langchain-hub/master/agents/"
|
||||
|
||||
Loading…
Reference in New Issue
Block a user