Random question and Answer generation while using ConversationalRetrievalChain

[codebyte17]

System Info

python 3.11 langchain 0.0.263.

Who can help?

@agol

Information

• [ ] The official example notebooks/scripts
• [ ] My own modified scripts

Related Components

• [X] LLMs/Chat Models
• [ ] Embedding Models
• [ ] Prompts / Prompt Templates / Prompt Selectors
• [ ] Output Parsers
• [ ] Document Loaders
• [X] Vector Stores / Retrievers
• [X] Memory
• [ ] Agents / Agent Executors
• [ ] Tools / Toolkits
• [X] Chains
• [ ] Callbacks/Tracing
• [ ] Async

Reproduction

I want to add memory into docs based question answer chatbot but after adding memory the chatbot randomly generate question and answer automatically.

Expected behavior

I need chatbot for docs based question answer and chat history.

[dosubot[bot]]

🤖

Hello,

Based on the information you've provided and the context from the repository, it seems like you're experiencing an issue with the ConversationalRetrievalChain generating random questions and answers after adding memory.

To address this, you might want to consider using the RocksetChatMessageHistory class provided in the LangChain framework. This class allows you to add and retrieve messages from a chat history stored in a Rockset database, which could help in maintaining the chat history and preventing the generation of random questions and answers. Here's a sample code snippet on how to use it:

from langchain.memory.chat_message_histories import RocksetChatMessageHistory
from rockset import RocksetClient

# Initialize the RocksetChatMessageHistory
history = RocksetChatMessageHistory(
    session_id="MySession",
    client=RocksetClient(),
    collection="langchain_demo",
    sync=True
)

# Add user and AI messages
history.add_user_message("hi!")
history.add_ai_message("whats up?")

# Retrieve and print the chat history
print(history.messages)

You can find more details about this in the RocksetChatMessageHistory documentation.

As for the changes in the LangChain version 0.0.264, I'm unable to provide specific details as I don't have that information. However, it's always a good idea to keep your software up-to-date, as newer versions often come with bug fixes and improvements that could potentially address your issue.

I hope this helps! If you have any more questions or need further clarification, feel free to ask.

Best, Dosu

Sources

• ConversationalRetrievalChain did not look into chat histroy while making an answer
• Is there no chain for question answer with sources and memory?
• libs/langchain/langchain/memory/chat_message_histories/rocksetdb.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[dosubot[bot]]

Hi, @codebyte17! I'm Dosu, and I'm helping the LangChain team manage their backlog. I wanted to let you know that we are marking this issue as stale.

From what I understand, the issue you raised was about the random generation of questions and answers when using the ConversationalRetrievalChain. In response, I suggested using the RocksetChatMessageHistory class provided in the LangChain framework to maintain the chat history and prevent the generation of random questions and answers. I also mentioned that it's a good idea to keep the software up-to-date for bug fixes and improvements.

Before we close this issue, we wanted to check with you if it is still relevant to the latest version of the LangChain repository. If it is, please let us know by commenting on the issue. Otherwise, feel free to close the issue yourself or it will be automatically closed in 7 days.

Thank you for your contribution to the LangChain repository!

[RohanSohani30]

did you find a solution to this issue?