[BUG] Using the API to call the Embedding model of Aliyun Tongyi Qianwen, it is unable to perform knowledge base question answering.

chatchat-space / Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM, Qwen 与 Llama 等）基于 Langchain 与 ChatGLM 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

Apache License 2.0

29.93k stars 5.24k forks source link

Problem Description When I use the Embedding model of Aliyun Tongyi Qianwen to perform vectorization operations, I am unable to perform knowledge base question answering. However, when I use the local bge-large-zh-v1.5 model for vectorization, I am able to perform knowledge base question answering.

Environment Information

langchain-ChatGLM version/commit number: (e.g., v2.0.1 or commit 123456):v2.0.1
Is Docker deployment used (yes/no): no
ChatGLM-6B / Model used (ChatGLM2-6B / Qwen-7B, etc.): use Qwen API
Vector library used (faiss, milvus, pg_vector, etc.): faiss
Operating system and version: windows10
Python version: 3.10

chatchat-space / Langchain-Chatchat

[BUG] Using the API to call the Embedding model of Aliyun Tongyi Qianwen, it is unable to perform knowledge base question answering. #4176