Comments (3)
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.
Details
Sources
- index.faiss和index.pkl这两个文件的具体作用是什么
- 如何选择Retriever
- 多路检索
- 如何提高知识库检索的正确性?
- 希望使用cosine sim来计算相似度,应该怎么用
- knowledge_base/samples/content/test_files/langchain-ChatGLM_closed.jsonl
- configs/kb_config.py.example
- server/agent/tools/search_knowledgebase_complex.py
- knowledge_base/samples/content/test_files/langchain-ChatGLM_open.jsonl
- server/reranker/reranker.py
- server/embeddings_api.py
About Dosu
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.
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?
Details
Sources
- 如何提升知识库对话文档检索的准确率
- 多路检索
- 如何提高知识库检索的正确性?
- server/api.py
- server/chat/knowledge_base_chat.py
- configs/kb_config.py.example
- server/agent/custom_agent/ChatGLM3Agent.py
- server/chat/search_engine_chat.py
About Dosu
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.
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.
Related Issues (20)
- 怎么调用昇腾服务器npu? HOT 1
- docker部署的milvus数据库有大量的数据,想直接迁移到其他机器上,可以吗?
- 分词和分块逻辑顺序
- [FEATURE] 在问答中能够返回PDF或者DOCX中的图片信息
- [BUG] 使用es作向量数据库时,某些markdown文档向量化失败 HOT 2
- v1/chat/completions
- The request client is not a secure context and the resource is in more-private address space。特殊跨域问题如何解决。
- 求助:python startup.py -a 报错assert r.status_code == 200 AssertionError HOT 1
- 求助:如何不使用api,批量进行预测 HOT 2
- 启动startup.py,即便显卡不存在运行进程,依然显示报错:torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 134.00 MiB. GPU 0 has a total capacty of 21.99 GiB of which 119.06 MiB is free HOT 2
- [BUG] 知识库名称使用中文出现错误 HOT 1
- 0.2.10版本,知识库,不能基于上次回答的内容连续对话。
- 0.2.10版本,知识库内容拆分,指定特殊分割符,没有效果。
- 0.2.10版本,知识库对话,多个问题回答不了。
- [BUG] glm-4-9b-chat模型运行问题 HOT 9
- 自动生成测试用例
- bge-m3无法检索到内容
- 项目首页底下 微信交流群二维码失效了
- embedding 模型可以换成在线的API吗,怎么换成在线的API
- 能支持glm-4-9b-chat吗模型配置文件里面好像没有
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from langchain-chatchat.