Jack 0d3e410826 fix: strip Ollama-style tag suffix from LocalAI model names (#15908) ...

## Summary

LocalAI exposes two API surfaces with conflicting naming conventions:
- `GET /api/tags` returns model names with `:latest` suffix (Ollama
format)
- `POST /v1/chat/completions` expects names without `:latest` (OpenAI
format)

RAGFlow discovered models via `/api/tags` and stored the tagged name,
then used it with `/v1/chat/completions`, causing a 404 error because
LocalAI didn't recognize `model:latest`.

## Fix

In `LocalAI.get_model_list()`, strip the tag suffix from model names
using `model["name"].rsplit(":", 1)[0]`, so stored names match what the
OpenAI-compatible endpoints expect.

2026-06-10 19:05:05 +08:00

..

agent

fix(browser): show resolved variables in workflow run log input (#15325)

2026-06-08 18:12:56 +08:00

api

Refactor: consolidate to use @login_required (#15652)

2026-06-05 11:35:00 +08:00

common

Fix wrong unit test path (#15864)

2026-06-09 22:48:33 +08:00

data_source

fix(onedrive): normalize folder_path for Graph delta URL (#15503)

2026-06-08 09:56:47 +08:00

deepdoc/parser

Fix wrong unit test path (#15864)

2026-06-09 22:48:33 +08:00

memory/utils

Test : aggregation edge cases for list and scalar values (#14170)

2026-05-12 15:53:35 +08:00

rag

fix: strip Ollama-style tag suffix from LocalAI model names (#15908)

2026-06-10 19:05:05 +08:00

test_test_chunk_feedback_package.py

Refa: GraphRAG to use async chat methods instead of thread pool execution (#14002)

2026-04-09 19:57:35 +08:00