This handoff doc was accidentally introduced by PR #18005 and should not
be part of the repository. Remove it to keep the tree clean.
Co-authored-by: xugangqiang <xugangqiang@users.noreply.github.com>
## What problem does this PR solve?
`TenantLLMService.model_instance` constructs vision providers with
`lang` as the third positional argument and `base_url` as a keyword
argument.
`LocalAICV` declared `base_url` as its third parameter, causing:
```text
TypeError: LocalAICV.__init__() got multiple values for argument 'base_url'
```
This prevents LocalAI vision models from being used during document
parsing.
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- Extends unit test coverage for
pi/apps/restful_apis/dify_retrieval_api.py (the Dify external knowledge
base endpoint).
Co-authored-by: zjm11902 <zjm11902@users.noreply.github.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Empty reply configured in knowledge base chat, no content returned when
matched empty content
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## What changed
- add an OceanBase/SeekDB Go document engine using `database/sql` and
the existing MySQL driver
- preserve the Python connector's configuration, physical table names,
schema, index names, and ARRAY/JSON/VECTOR encodings
- implement chunk, memory, document metadata, skill, SQL, full-text,
vector, and fusion search paths
- support `DBMS_HYBRID_SEARCH.SEARCH` behind the existing feature flag,
with SQL fallback only when the package is unavailable
- wire the engine into retrieval, memory, metadata, vector hydration,
and SQL chat flows
- add Python/Go compatibility contracts, SQL mock tests, and an
integration-tagged round-trip test
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
chore(rag/app): remove stray debug print() calls
Two hot-path debug print() calls were leaking content/error text to
stdout in production code paths.
* rag/app/naive.py: TxtParser branch in chunk() was printing the entire
parsed sections list (formatted via repr()) wrapped in 150-char banner
lines. For large text documents (e.g. a 1000+-page book ingest) this
dumped tens of thousands of lines per ingest into the docker logs.
Replaced with a structured
`logging.info("TxtParser produced %d sections for %s", len(sections),
filename)` so the parse count is still observable without the content
leak.
* rag/app/presentation.py: Pdf.position parsing had a debug
`print(f"Error parsing position: {e}")` inside an except clause in the
ingest hot path. Replaced with
`logging.warning(f"Error parsing position in {filename}: {e}")` to
match the file's existing logging pattern and add filename context.
Both call sites already had logging imported; no new imports added.
logging was used throughout the surrounding code in the same
logging.{info,warning,error}(...) style.
Aligns the Go EML parser (`internal/parser/parser/email_parser.go`) with the Python flow parser (`rag/flow/parser/parser.py:_email`) on two structural points so the Go path is a faithful drop-in for the Python path on `.eml` inputs.
Unifies the Go TokenChunker merge path on a single `mergeUnits` core and
fixes coordinate-tag drift in the Python JSON merge at `overlap > 0`.
Rebased on top of #17979 (delimiter_mode convergence).
Re-materialize wiki page graph from merged wiki_page rows after each
batch merge. Adds ProjectWikiGraph/DropWikiGraph, full page_type/slug
identity, delete-then-insert, tests.
### What problem does this PR solve?
`NvidiaRerank.__init__` only assigned `self.base_url` inside two
model-specific
`if` branches:
```python
if self.model_name == "nvidia/nv-rerankqa-mistral-4b-v3":
self.base_url = urljoin(base_url, "nv-rerankqa-mistral-4b-v3/reranking")
if self.model_name == "nvidia/rerank-qa-mistral-4b":
self.base_url = urljoin(base_url, "reranking")
```
Any other NVIDIA rerank model therefore left the attribute unset, and
the first
`_compute_rank()` call died with `AttributeError: 'NvidiaRerank' object
has no
attribute 'base_url'`.
This is reachable in normal use: `conf/llm_factories.json` ships no
NVIDIA
rerank entries at all, so every NVIDIA rerank model has to be added by
hand,
and any name other than those two hardcoded strings crashes.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Alex Ma <alex_makang@hotmail.com>
Converge `TokenChunker.delimiter_mode` from three values (`token_size`,
`delimiter`, `one`) to two (`delimiter`, `one`). The unified `delimiter`
mode now carries the old `token_size` semantics: when no active
(backtick) delimiter is present, text/JSON chunks are merged up to
`chunk_token_size`; when a backtick delimiter is present, the text is
split by it and not merged. `one` continues to be handled by the
separate `OneChunker`.
