Langchain-Chatchat向量检索方式 about langchain-chatchat HOT 3 OPEN

Langchain-Chatchat utilizes vector retrieval for indexing local knowledge and converting questions into vectors, aiming to meet semantic search requirements. It doesn't explicitly mention the use of inverted indexing or vector recall methods in the documentation. However, the configuration VECTOR_SEARCH_TOP_K = 3 suggests a multi-path recall approach during vector retrieval, indicating that the system considers multiple potential matches by retrieving the top 3 vectors closest to the query vector. This setup implies a focus on enhancing the relevance and accuracy of the search results by evaluating several possible answers.

To continue the conversation, mention @dosu.

from langchain-chatchat.

Langchain-Chatchat currently supports multi-path retrieval/recall as indicated by its configuration to retrieve the top 3 most similar vectors for a given query. This setup allows the system to consider multiple potential matches, enhancing the relevance and accuracy of search results. The knowledge_base_chat function further processes these retrieved documents, potentially using a re-ranker to refine the selection based on relevance.

As for the upcoming 0.3 version and specific plans regarding the implementation or improvement of multi-path retrieval/recall, there's no publicly documented information available in the repository. For more detailed insights or future plans about multi-path retrieval/recall in Langchain-Chatchat, it might be beneficial to directly reach out to the maintainers.

@zrzrzrzrzrzrzrzr, could you provide more details on whether multi-path retrieval/recall will be supported or enhanced in the upcoming 0.3 version?

To continue the conversation, mention @dosu.

from langchain-chatchat.

@dosu, 根据问题#3563的回答，现在是不支持多路检索/多路召回吗？
@zRzRzRzRzRzRzR 维护者你好，现在的版本是仍然不支持吗，之后的0.3版本考虑更新吗？

from langchain-chatchat.