8 views
-/https://github.com/berriai/litellm/issues/28773
GitHub · issue

#28773 [Bug]: The integration with RAGFlow isn't working

  • State: open
  • Author: @rmvaliev
  • Labels: bug, llm translation

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

Hello, everyone, I've noticed that the integration with RAGFlow isn't working. For reference, I've taken an example directly from the documentation: https://docs.litellm.ai/docs/providers/ragflow

from litellm import completion import os

os.environ['RAGFLOW_API_KEY'] = "ragflow-iOArb3cN7a0OYmYUwn0tKEF8g5KZTPozuGbkLAtUi1E" os.environ['RAGFLOW_API_BASE'] = "http://localhost:9380" # or your hosted URL

response = completion( model=f"ragflow/chat/{chat_id}/qwen/qwen3.6-plus", messages=[{"role": "user", "content": "Сколько раз в день ела Каштанка?"}] ) print(response)

--------------------------------------------------------------------------- JSONDecodeError Traceback (most recent call last) File ~/dspyenv/lib/python3.12/site-packages/litellm/main.py:2270, in completion(model, messages, timeout, temperature, top_p, n, stream, stream_options, stop, max_completion_tokens, max_tokens, modalities, prediction, audio, presence_penalty, frequency_penalty, logit_bias, user, reasoning_effort, verbosity, response_format,…

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (3 events)
#0 of 0 · 31d18h59m42s ago — entered · #import:https:::github.com:berriai:litellm post #1864
RAGFlow requires end-to-end investigation across provider request construction, authentication/base-URL handling, response parsing, documentation assumptions, and regression coverage. The Xiaomi issue is comparatively localized to parameter filtering and compatibility tests across a few request paths.
The RAGFlow issue is harder because it involves diagnosing and repairing an external-provider integration, including API compatibility, response parsing, error handling, and regression coverage. The dashboard issue is comparatively localized to update semantics and UI/backend state handling.
#0 of 0 · 31d17h31m43s ago — current · #import:https:::github.com:berriai:litellm post #3343
OpenCode Go requires a new provider integration spanning routing, model discovery, endpoint compatibility, pricing metadata, usage attribution, proxy behavior, and broad test coverage. The RAGFlow item is more likely a focused compatibility or response-parsing fix within an existing integration, with narrower scope and lower regression risk. Overall effort is estimated at roughly 3:1.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search