Spaces:

spark-ds549
/

LibRAG

Runtime error

daniel Foley commited on Nov 27, 2024

Commit

91b7015

1 Parent(s): 74eb75e

Sample Chainlit app placeholder

Co-authored-by: Dan [email protected]
Co-authored-by: Brandon [email protected]
Co-authored-by: Enrico [email protected]

Files changed (3) hide show

Dockerfile +1 -1
app.py +79 -131
requirements.txt +6 -4

Dockerfile CHANGED Viewed

	@@ -62,7 +62,7 @@ COPY --chown=user ./requirements.txt requirements.txt
62
63
64
65	- RUN pip install --no-cache-dir ~~--upgrade~~ -r requirements.txt
66
67
68


62
63
64
65	+ RUN pip install --no-cache-dir -r requirements.txt
66
67
68

app.py CHANGED Viewed

@@ -1,265 +1,213 @@
-import chainlit as cl
-from typing import Optional
-import time
-# Store conversation history
-conversation_memory = []
-@cl.on_chat_start
-async def start():
-    """Initializes the chat session"""
-    # Send an initial message
-    await cl.Message(
-        content="👋 Hello! I'm your AI assistant. How can I help you today?",
-        author="Assistant"
-    ).send()
-    # Set some session variables
-    cl.user_session.set("conversation_started", True)
-@cl.on_message
-async def main(message: cl.Message):
-    """Main message handler"""
-    # Simulate some processing time
-    with cl.Step("Processing...") as step:
-        time.sleep(1)  # Simulated delay
-        step.output = "Processed message"
-    # Store message in conversation history
-    conversation_memory.append({
-        "role": "user",
-        "content": message.content
-    })
-    # Create a response
-    response = f"I received your message: '{message.content}'. This is a demo response."
-    # Store response in conversation history
-    conversation_memory.append({
-        "role": "assistant",
-        "content": response
-    })
-    # Send response with typing effect
-    await cl.Message(
-        content=response,
-        author="Assistant"
-    ).send()
-@cl.password_auth_callback
-def auth_callback(username: str, password: str) -> Optional[cl.User]:
-    """Basic authentication handler"""
-    # This is a simple example - in production, use proper authentication
-    if username == "demo" and password == "password":
-        return cl.User(identifier="demo", metadata={"role": "user"})
-    return None
-@cl.on_chat_end
-async def end():
-    """Cleanup when chat ends"""
-    await cl.Message(content="👋 Thank you for chatting! Goodbye!").send()
-# Custom action handler example
-@cl.action_callback("feedback")
-async def on_action(action):
-    """Handles custom feedback action"""
-    await cl.Message(content=f"Received feedback: {action.value}").send()

+import os
+from typing import List
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+from langchain.chains import (
+    ConversationalRetrievalChain,
+)
+from langchain.chat_models import ChatOpenAI
+from langchain.docstore.document import Document
+from langchain.memory import ChatMessageHistory, ConversationBufferMemory
+import chainlit as cl
+os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+@cl.on_chat_start
+async def on_chat_start():
+    files = None
+    # Wait for the user to upload a file
+    while files == None:
+        files = await cl.AskFileMessage(
+            content="Please upload a text file to begin!",
+            accept=["text/plain"],
+            max_size_mb=20,
+            timeout=180,
+        ).send()
+    file = files[0]
+    msg = cl.Message(content=f"Processing `{file.name}`...")
+    await msg.send()
+    with open(file.path, "r", encoding="utf-8") as f:
+        text = f.read()
+    # Split the text into chunks
+    texts = text_splitter.split_text(text)
+    # Create a metadata for each chunk
+    metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]
+    # Create a Chroma vector store
+    embeddings = OpenAIEmbeddings()
+    docsearch = await cl.make_async(Chroma.from_texts)(
+        texts, embeddings, metadatas=metadatas
+    )
+    message_history = ChatMessageHistory()
+    memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        output_key="answer",
+        chat_memory=message_history,
+        return_messages=True,
+    )
+    # Create a chain that uses the Chroma vector store
+    chain = ConversationalRetrievalChain.from_llm(
+        ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, streaming=True),
+        chain_type="stuff",
+        retriever=docsearch.as_retriever(),
+        memory=memory,
+        return_source_documents=True,
+    )
+    # Let the user know that the system is ready
+    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
+    await msg.update()
+    cl.user_session.set("chain", chain)
+@cl.on_message
+async def main(message: cl.Message):
+    chain = cl.user_session.get("chain")  # type: ConversationalRetrievalChain
+    cb = cl.AsyncLangchainCallbackHandler()
+    res = await chain.acall(message.content, callbacks=[cb])
+    answer = res["answer"]
+    source_documents = res["source_documents"]  # type: List[Document]
+    text_elements = []  # type: List[cl.Text]
+    if source_documents:
+        for source_idx, source_doc in enumerate(source_documents):
+            source_name = f"source_{source_idx}"
+            # Create the text element referenced in the message
+            text_elements.append(
+                cl.Text(content=source_doc.page_content, name=source_name, display="side")
+            )
+        source_names = [text_el.name for text_el in text_elements]
+        if source_names:
+            answer += f"\nSources: {', '.join(source_names)}"
+        else:
+            answer += "\nNo sources found"
+    await cl.Message(content=answer, elements=text_elements).send()

requirements.txt CHANGED Viewed

@@ -1,9 +1,11 @@
-fastapi
-uvicorn[standard]
-chainlit

+chainlit==1.3.0
+langchain
+langchain-community
+pydantic==2.7.3
+pydantic-settings==2.6.1
+pydantic_core==2.18.4