[BUG] 简洁阐述问题 / Concise description of the issue

[RATOR-codes]

问题描述 / Problem Description
更换系统所调用的模型为deepseek API，在使用RAG功能时会出现下面报错，请问有什么解决办法？

2025-03-27 13:28:40,497 httpx 6934 INFO HTTP Request: POST https://api.deepseek.com/v1/embeddings "HTTP/1.1 404 Not Found"
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/root/miniconda3/envs/chatchat/lib/python3.8/site-packages/sse_starlette/sse.py", line 269, in call
await wrap(partial(self.listen_for_disconnect, receive))
File "/root/miniconda3/envs/chatchat/lib/python3.8/site-packages/sse_starlette/sse.py", line 258, in wrap
await func()
File "/root/miniconda3/envs/chatchat/lib/python3.8/site-packages/sse_starlette/sse.py", line 215, in listen_for_disconnect
message = await receive()
File "/root/miniconda3/envs/chatchat/lib/python3.8/site-packages/uvicorn/protocols/http/h11_impl.py", line 524, in receive
await self.message_event.wait()
File "/root/miniconda3/envs/chatchat/lib/python3.8/asyncio/locks.py", line 309, in wait
await fut
asyncio.exceptions.CancelledError

复现问题的步骤 / Steps to Reproduce

1. 执行 '...' / Run '...'
2. 点击 '...' / Click '...'
3. 滚动到 '...' / Scroll to '...'
4. 问题出现 / Problem occurs

预期的结果 / Expected Result
描述应该出现的结果 / Describe the expected result.

实际结果 / Actual Result
描述实际发生的结果 / Describe the actual result.

环境信息 / Environment Information

• Langchain-Chatchat 版本 / commit 号：(例如：0.3.1 或 commit 123456) / Langchain-Chatchat version / commit number: (e.g., 0.3.1 or commit 123456)
• 部署方式（pypi 安装 / 源码部署 / docker 部署）：pypi 安装 / Deployment method (pypi installation / dev deployment / docker deployment): pypi installation
• 使用的模型推理框架（Xinference / Ollama / OpenAI API 等）：Xinference / Model serve method（Xinference / Ollama / OpenAI API, etc.): Xinference
• 使用的 LLM 模型（GLM-4-9B / Qwen2-7B-Instruct 等）：GLM-4-9B / LLM used (GLM-4-9B / Qwen2-7B-Instruct, etc.): GLM-4-9B
• 使用的 Embedding 模型（bge-large-zh-v1.5 / m3e-base 等）：bge-large-zh-v1.5 / Embedding model used (bge-large-zh-v1.5 / m3e-base, etc.): bge-large-zh-v1.5
• 使用的向量库类型 (faiss / milvus / pg_vector 等)： faiss / Vector library used (faiss, milvus, pg_vector, etc.): faiss
• 操作系统及版本 / Operating system and version: MacOS
• Python 版本 / Python version: 3.8
• 推理使用的硬件（GPU / CPU / MPS / NPU 等） / Inference hardware (GPU / CPU / MPS / NPU, etc.): GPU
• 其他相关环境信息 / Other relevant environment information:

附加信息 / Additional Information
添加与问题相关的任何其他信息 / Add any other information related to the issue.

[dosubot]

@RATOR-codes 你好，我是Dosu。我可以帮助你解决 bug、回答问题，还可以帮助你成为贡献者。在等待人类维护者的过程中，我会尽力帮助你。

I found a similar open issue related to a 404 error when using the Deepseek API. The suggested solution is to ensure you are accessing the correct endpoint. For API requests, you should use one of the following endpoints:

• /chat/chat
• /chat/search_engine_chat
• /chat/feedback
• /llm_model/list_running_models
• /llm_model/list_config_models
• /llm_model/get_model_config
• /llm_model/stop
• /llm_model/change
• /server/configs
• /server/list_search_engines
• /server/get_prompt_template
• /other/completion
• /other/embed_texts

These endpoints are all POST requests. Additionally, consider changing the openai_api_port in server/llm_api.py and api_base_url in configs/model_config.py to avoid port conflicts ^[1].

For the specific issue with the Deepseek API, ensure that the endpoint URL is correct and that the API is properly configured to handle requests. The '/embeddings' endpoint in the Deepseek API is used to vectorize text, and it should return embeddings in the format BaseResponse(data=List[List[float]]) ^[2]. Double-check the endpoint URL and the parameters being sent in the request.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}