Rander 62698725ca feat(paddleocr): add image parsing support with async Job API (#16086) ...

## Summary

Add image parsing capability to PaddleOCR integration, building on top
of #15967 (async Job API migration).

## Changes

### `deepdoc/parser/paddleocr_parser.py`
- Add `parse_image()` method that uses the same async Job API flow as
`parse_pdf()`
- Extracts text from `layoutParsingResults` → `prunedResult` →
`parsing_res_list`
- Returns concatenated block content as a single string

### `rag/llm/ocr_model.py`
- Add `parse_image()` wrapper to `PaddleOCROcrModel` with availability
check and logging

## Relationship to other PRs

- **Depends on**: #15967 (async Job API migration) — this PR is based on
that branch
- **Replaces**: #14826 (original image processing PR based on old sync
API)

## Notes

This PR uses `base_url` and the async Job API (submit → poll → fetch)
consistent with #15967, rather than the old `api_url` + sync POST
pattern from #14826.

2026-06-16 19:34:38 +08:00

..

__init__.py

Fix: cohere call failing (#15899)

2026-06-10 15:57:10 +08:00

chat_model.py

fix: replicate model provider (#15933)

2026-06-11 15:08:33 +08:00

cv_model.py

fix: tolerate raw api_key string in AzureEmbed and AzureGptV4 __init__ (#15877)

2026-06-11 16:28:29 +08:00

embedding_model.py

fix(llm): correct error handling, token accounting, and truncation in embedding providers (#15424)

2026-06-11 19:29:46 +08:00

key_utils.py

fix: replicate model provider (#15933)

2026-06-11 15:08:33 +08:00

model_meta.py

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

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

ocr_model.py

feat(paddleocr): add image parsing support with async Job API (#16086)

2026-06-16 19:34:38 +08:00

rerank_model.py

fix: handle qwen rerank error response (#15881)

2026-06-10 13:05:24 +08:00

sequence2txt_model.py

fix(llm): add timeout to HTTP requests in LLM integration layer (#14313)

2026-05-11 11:19:07 +08:00

tool_decorator.py

Feat: @tool decorator for chat-model tool registration (#15047)

2026-05-21 15:32:17 +08:00

tts_model.py

fix(llm): add timeout to HTTP requests in LLM integration layer (#14313)

2026-05-11 11:19:07 +08:00