Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUG] Sherpa Does Not Recover From previous Failures #265

Open
20001LastOrder opened this issue Dec 14, 2023 · 0 comments
Open

[BUG] Sherpa Does Not Recover From previous Failures #265

20001LastOrder opened this issue Dec 14, 2023 · 0 comments
Labels
bug Something isn't working

Comments

@20001LastOrder
Copy link
Collaborator

Describe the bug
Check the following chat history with Sherpa:

User: [@Sherpa](https://aisc-to.slack.com/team/U05E3C72K19)
 compare LLamaIndex and Langchain

Sherpa: LLamaIndex is a simple, flexible data framework for connecting custom data sources to large language models (LLMs) [[1]](https://gpt-index.readthedocs.io/). It allows users to ingest, structure, and access private or domain-specific data for LLM-based applications [[2]](https://github.com/run-llama/llama_index). LlamaIndex provides tools for both beginner and advanced users, with a high-level API for easy data ingestion and querying [[3]](https://huggingface.co/llamaindex). It serves as a central interface to connect LLMs with external data [[4]](https://www.datacamp.com/tutorial/llama-index-adding-personal-data-to-llms). With LlamaIndex, users can easily manage and retrieve private and domain-specific data using natural language [[5]](https://nanonets.com/blog/llamaindex/). There is also a complete tutorial available that discusses how to connect data to LLMs and perform tasks with natural language .
As for Langchain, I couldn't find any information about it. Would you like me to search for Langchain as well?

[User: @Sherpa](https://aisc-to.slack.com/team/U05E3C72K19)
 compare with LangChain

Sherpa: I couldn't find any information about LangChain.

Sherpa could not find information about LangChain because currently it only does search once. It searched LLamaIndex. See below:
image

Then, when the question is asked again, Sherpa 'gives up' on finding information because of the previous information in the context. See below:

image

To Reproduce
Steps to reproduce the behavior:

  1. Ask Sherpa to compare LangChain and LlamaIndex
  2. Try until Sherpa does not identify information about LangChain or LLamaIndex
  3. Ask Sherpa about the one that was not identified again.

Expected behavior
Sherpa should be able to identify the previous unfound information wit ha new search query.

@20001LastOrder 20001LastOrder added the bug Something isn't working label Dec 14, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant