Add LangChain Proofreading Bot example (#8)

* Add LangChain Proofreading Bot example

* Refine README.md

* Update examples/proofreading-bot-langchain/main.py

Co-authored-by: Byeonghoon Yoo <[email protected]>

---------

Co-authored-by: Byeonghoon Yoo <[email protected]>

examples/proofreading-bot-langchain/README.md

@@ -0,0 +1,41 @@
+# PlugBear Python SDK Example (LangChain)
+
+This project introduces an example of integrating a LangChain application with
+communication channels, such as Slack, using PlugBear. Check [Building a Proofreading Bot Using LangChain](http://localhost:3001/use-cases/proofreading-bot/langchain) for detailed guide.
+
+## Prerequisites
+
+- [Poetry](https://python-poetry.org)
+
+## Development
+
+### Installing Dependencies
+
+Use [Poetry](https://python-poetry.org/) to install dependencies.
+
+```bash
+poetry install
+```
+
+### Running Server
+
+Run the command below to run the server:
+
+```bash
+OPENAI_API_KEY="YOUR_OPENAI_API_KEY" \
+  PLUGBEAR_API_KEY="YOUR_PLUGBEAR_API_KEY" \
+  poetry run python main.py
+```
+
+You can obtain your `OPENAI_API_KEY` from the
+[OpenAI API Keys](https://platform.openai.com/api-keys) page, and your
+`PLUGBEAR_API_KEY` from the
+[PlugBear API Keys](https://auth.plugbear.io/org/api_keys) page.
+
+### Testing Integration
+
+Follow [PlugBear Documentation](https://docs.plugbear.io) to connect your app
+into communication channels and test it.
+
+Ask any math question to `@PlugBear` after connecting it. e.g.,
+``@PlugBear This is an example sentence.``.

examples/proofreading-bot-langchain/main.py

@@ -0,0 +1,58 @@
+from __future__ import annotations
+
+import contextlib
+import os
+from collections.abc import AsyncGenerator
+
+from fastapi import FastAPI
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+
+import plugbear.fastapi
+
+OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]
+PLUGBEAR_API_KEY = os.environ["PLUGBEAR_API_KEY"]
+
+llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY)
+
+
+async def handle_request(request: plugbear.fastapi.Request) -> str:
+    """ Handle the request received from PlugBear.
+    """
+
+    # Convert PlugBear messages to LangChain messages.
+    messages = [(message.role, message.content)
+                for message in request.messages]
+
+    # Build prompt using the system message and PlugBear messages.
+    system_prompt = ("system", "You are the Proofreading Bot, an editor bot designed to proofread technical manuals with the precision and style of a professional technical writer. Your primary function is to make the text clear, concise, and professional. You avoid jargon, ambiguous expressions, and emotional language, aiming for straightforward, easy-to-understand, yet professional sentences. You specialize in improving the readability and accuracy of technical manuals, adhering to high standards of technical writing. While maintaining professionalism, your interaction style is helpful, providing guidance and suggestions to enhance the user's text. Answer the revised version of the text only. Do not add any other descriptions.")
+    prompt = ChatPromptTemplate.from_messages(
+        [system_prompt] + messages)
+
+    # Invoke the LangChain pipeline.
+    output_parser = StrOutputParser()
+    chain = prompt | llm | output_parser
+    answer = chain.invoke({})
+
+    # Returning the generated message.
+    return answer
+
+
+@contextlib.asynccontextmanager
+async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
+    await plugbear.fastapi.register(
+        app,
+        llm_func=handle_request,
+        api_key=PLUGBEAR_API_KEY,
+        endpoint="/plugbear",
+    )
+    yield
+
+
+app = FastAPI(lifespan=lifespan)
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PORT", default=8000)))