add retrieval agent (langchain-ai#13317)

templates/retrieval-agent/.gitignore

@@ -0,0 +1 @@
+__pycache__

templates/retrieval-agent/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 LangChain, Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

templates/retrieval-agent/README.md

@@ -0,0 +1,74 @@
+# retrieval-agent
+
+This package uses Azure OpenAI to do retrieval using an agent architecture.
+By default, this does retrieval over Arxiv.
+
+## Environment Setup
+
+Since we are using Azure OpenAI, we will need to set the following environment variables:
+
+```shell
+export AZURE_OPENAI_API_BASE=...
+export AZURE_OPENAI_API_VERSION=...
+export AZURE_OPENAI_API_KEY=...
+export AZURE_OPENAI_DEPLOYMENT_NAME=...
+```
+
+## Usage
+
+To use this package, you should first have the LangChain CLI installed:
+
+```shell
+pip install -U langchain-cli
+```
+
+To create a new LangChain project and install this as the only package, you can do:
+
+```shell
+langchain app new my-app --package retrieval-agent
+```
+
+If you want to add this to an existing project, you can just run:
+
+```shell
+langchain app add retrieval-agent
+```
+
+And add the following code to your `server.py` file:
+```python
+from retrieval_agent import chain as retrieval_agent_chain
+
+add_routes(app, retrieval_agent_chain, path="/retrieval-agent")
+```
+
+(Optional) Let's now configure LangSmith. 
+LangSmith will help us trace, monitor and debug LangChain applications. 
+LangSmith is currently in private beta, you can sign up [here](https://smith.langchain.com/). 
+If you don't have access, you can skip this section
+
+
+```shell
+export LANGCHAIN_TRACING_V2=true
+export LANGCHAIN_API_KEY=<your-api-key>
+export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"
+```
+
+If you are inside this directory, then you can spin up a LangServe instance directly by:
+
+```shell
+langchain serve
+```
+
+This will start the FastAPI app with a server is running locally at 
+[http://localhost:8000](http://localhost:8000)
+
+We can see all templates at [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)
+We can access the playground at [http://127.0.0.1:8000/retrieval-agent/playground](http://127.0.0.1:8000/retrieval-agent/playground)  
+
+We can access the template from code with:
+
+```python
+from langserve.client import RemoteRunnable
+
+runnable = RemoteRunnable("http://localhost:8000/retrieval-agent")
+```

templates/retrieval-agent/pyproject.toml

@@ -0,0 +1,25 @@
+[tool.poetry]
+name = "retrieval-agent"
+version = "0.0.1"
+description = ""
+authors = []
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.313, <0.1"
+openai = "^0.28.1"
+arxiv = "^2.0.0"
+
+[tool.poetry.group.dev.dependencies]
+langchain-cli = ">=0.0.4"
+fastapi = "^0.104.0"
+sse-starlette = "^1.6.5"
+
+[tool.langserve]
+export_module = "retrieval_agent"
+export_attr = "agent_executor"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

templates/retrieval-agent/retrieval_agent/__init__.py

@@ -0,0 +1,3 @@
+from retrieval_agent.chain import agent_executor
+
+__all__ = ["agent_executor"]

templates/retrieval-agent/retrieval_agent/chain.py

@@ -0,0 +1,75 @@
+import os
+from typing import List, Tuple
+
+from langchain.agents import AgentExecutor
+from langchain.agents.format_scratchpad import format_to_openai_function_messages
+from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser
+from langchain.chat_models import AzureChatOpenAI
+from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain.pydantic_v1 import BaseModel, Field
+from langchain.schema.messages import AIMessage, HumanMessage
+from langchain.tools import ArxivQueryRun
+from langchain.tools.render import format_tool_to_openai_function
+from langchain.utilities import ArxivAPIWrapper
+
+
+class ArxivInput(BaseModel):
+    query: str = Field(description="search query to look up")
+
+
+# Create the tool
+arxiv_tool = ArxivQueryRun(api_wrapper=ArxivAPIWrapper(), args_schema=ArxivInput)
+tools = [arxiv_tool]
+llm = AzureChatOpenAI(
+    temperature=0,
+    deployment_name=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
+    openai_api_base=os.environ["AZURE_OPENAI_API_BASE"],
+    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
+    openai_api_key=os.environ["AZURE_OPENAI_API_KEY"],
+)
+assistant_system_message = """You are a helpful research assistant. \
+Lookup relevant information as needed."""
+prompt = ChatPromptTemplate.from_messages(
+    [
+        ("system", assistant_system_message),
+        MessagesPlaceholder(variable_name="chat_history"),
+        ("user", "{input}"),
+        MessagesPlaceholder(variable_name="agent_scratchpad"),
+    ]
+)
+
+llm_with_tools = llm.bind(functions=[format_tool_to_openai_function(t) for t in tools])
+
+
+def _format_chat_history(chat_history: List[Tuple[str, str]]):
+    buffer = []
+    for human, ai in chat_history:
+        buffer.append(HumanMessage(content=human))
+        buffer.append(AIMessage(content=ai))
+    return buffer
+
+
+agent = (
+    {
+        "input": lambda x: x["input"],
+        "chat_history": lambda x: _format_chat_history(x["chat_history"]),
+        "agent_scratchpad": lambda x: format_to_openai_function_messages(
+            x["intermediate_steps"]
+        ),
+    }
+    | prompt
+    | llm_with_tools
+    | OpenAIFunctionsAgentOutputParser()
+)
+
+
+class AgentInput(BaseModel):
+    input: str
+    chat_history: List[Tuple[str, str]] = Field(
+        ..., extra={"widget": {"type": "chat", "input": "input", "output": "output"}}
+    )
+
+
+agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True).with_types(
+    input_type=AgentInput
+)