gpt-open / rag-gpt Goto Github PK

Should not return empty sources

Does it support local large models?

Does rag gpt support parsing images and tables in PDFs?

I want to use Deepseek instead of openai.
It's a cost-effective solution with high performance.

The Docker deployment in the Windows environment is not started
web-1exec /start.sh:no such file or directory

Add a human online customer service system.

cat .env
LLM_NAME="Ollama"
OLLAMA_MODEL_NAME="qwen:7b"
OLLAMA_BASE_URL="http://192.168.2.205:11434"
MIN_RELEVANCE_SCORE=0.3
BOT_TOPIC="OpenIM"
URL_PREFIX="http://192.168.2.205:11434"
USE_PREPROCESS_QUERY=0
USE_RERANKING=1
USE_DEBUG=1

Error reporting:

192.168.2.205 - - [19/May/2024 01:08:06] "POST /open_kf_api/queries/smart_query_stream HTTP/1.1" 500 -
Error on request:
Traceback (most recent call last):
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/werkzeug/serving.py", line 362, in run_wsgi
execute(self.server.app)
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/werkzeug/serving.py", line 325, in execute
for data in application_iter:
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/werkzeug/wsgi.py", line 256, in next
return self._next()
^^^^^^^^^^^^
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/werkzeug/wrappers/response.py", line 32, in _iter_encoded
for item in iterable:
File "/root/rag-gpt/server/app/queries.py", line 437, in generate_llm
response = generate_answer(query, user_id, True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/rag-gpt/server/app/queries.py", line 305, in generate_answer
response = llm_generator.generate(prompt, is_streaming)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/rag-gpt/server/rag/generation/llm.py", line 47, in generate
response = self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/openai/_utils/_utils.py", line 275, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/openai/resources/chat/completions.py", line 663, in create
return self._post(
^^^^^^^^^^^
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/openai/_base_client.py", line 1200, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/openai/_base_client.py", line 889, in request
return self._request(
^^^^^^^^^^^^^^
File "/root/rag-gpt/myenv/lib/python3.11/site-packages/openai/_base_client.py", line 980, in _request
raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: 404 page not found

我添加了一个pdf文件作为数据，数据库有数据

，但是我打开机器人测试的时候输出Internal Server Error，
查看控制台是

ValueError: Expected each embedding in the embeddings to be a non-empty list, got empty embedding at pos 0

请问一下这种情况应该如何处理，我本身技术比较差，可能无法提供更有效的信息

Support for deploying local LLMs through Ollama is already available.

pdf, word, excel, markdown, txt, etc.

Documents with low query relevance can be filtered out.