## Problem
When users configure auto-metadata for a dataset, parsing crashes with:
```
KeyError: 'properties' in gen_metadata → schema["properties"]
```
## Root Cause
Pydantic `AutoMetadataField` defaults `enum` and `description` to `None`
when the frontend omits these fields:
```python
class AutoMetadataField(Base):
enum: Annotated[list[str] | None, Field(default=None)]
description: Annotated[str | None, Field(default=None)]
```
These `None` values propagate through the call chain and cause two
crashes:
### What problem does this PR solve?
Dedup api_key and migrate `is_tools `in migration.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
When setting the API key for the BaiduYiyan provider, all model
validations fail with the error "Fail to access model using this api
key. No valid response received".
**Root cause:**
1. `BaiduYiyanChat` in `rag/llm/chat_model.py` does not override
`async_chat_streamly()`. The `verify_api_key()` function uses
`mdl.async_chat_streamly()` to validate, but `BaiduYiyanChat` inherits
`Base.async_chat_streamly()` which uses the OpenAI client, not the Baidu
Qianfan SDK (qianfan). Since BaiduYiyan has no OpenAI-compatible
base_url, validation always fails.
2. `verify_api_key()` in `provider_api_service.py` does not format the
raw API key string into the JSON format (`{"yiyan_ak": "...",
"yiyan_sk": "..."}`) that `BaiduYiyanChat.__init__()` expects via
`json.loads(key)`.
**Fix:**
1. Add `async_chat_streamly()` method to `BaiduYiyanChat` using the
qianfan SDK, consistent with the existing `chat_streamly()` method.
2. Add BaiduYiyan API key formatting in `provider_api_service.py`
`verify_api_key()` to match the format expected by
`BaiduYiyanChat.__init__()`.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Force image parser runtime output format to JSON so downstream chunking
reads OCR results from the JSON output and image parser chunks can be
displayed.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Wang Qi <wangq8@outlook.com>
### What problem does this PR solve?
The last column definition `INDEX idx_instance_id (instance_id),` in the
`CREATE TABLE tenant_model` statement has a trailing comma, which causes
a MySQL syntax error during deployment.
Closes#15832
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### How was this tested?
- [x] Visual inspection: the trailing comma on line 837 has been removed
### What problem does this PR solve?
Propagate `tenant_id` from memory task messages into task collection so
refactored task execution can build a valid context.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Description
This PR ports the `GET /api/v1/agents/prompts` endpoint from the Python
backend to the Go backend.
### Changes Made
- **Handler**: Added `GetPrompts` method to `internal/handler/agent.go`.
- **Router**: Registered the `agents.GET("/prompts")` route in
`internal/router/router.go`.
- **Logic**: Leveraged the existing `service.LoadPrompt` utility to read
`analyze_task_system`, `analyze_task_user`, `next_step`, `reflect`, and
`citation_prompt` templates directly from the `rag/prompts` directory.
- **Unit Test**: Added `TestGetPrompts_Success` to
`internal/handler/agent_test.go` to mock the HTTP context and validate
the JSON response structure.
### Motivation
This is part of the ongoing effort to port the Agent API surface to Go.
Since this specific endpoint only serves static prompt templates and
does not require the complex DAG/Canvas execution engine, it can be
seamlessly and safely handled by the Go backend.
### Testing
- [x] Added automated unit test `TestGetPrompts_Success` (verified
passing).
- [x] Tested locally via `curl` against the Go server (port 9380) and
Python server (port 9384).
- [x] Verified that the Go JSON response structure and loaded prompt
text are logically 100% identical to the Python implementation.
### What problem does this PR solve?
Fix: An error message appears when accessing the agent's launch page:
"pagesize exceeds maximum value".
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: balibabu <assassin_cike@163.com>
## Summary
This PR adds checkpoint/resume support for the GraphRAG
`extract_community` and `resolve_entities` stages.
The implementation stores successful intermediate results in the
document store so interrupted ingestion can resume without repeating
already-completed LLM work. Checkpoints are loaded before each stage,
reused when available, saved after successful batch/community
processing, and cleaned up after the stage completes successfully.
## Related Issue
Closes: #15518
## Change Type
- [x] Feature
- [x] Bug fix
- [x] Test
- [ ] Refactor
- [ ] Documentation
- [ ] Breaking change
## Real Behavior Proof
Validation commands run locally:
```bash
uv run python -m py_compile \
rag/graphrag/checkpoints.py \
rag/graphrag/general/community_reports_extractor.py \
rag/graphrag/entity_resolution.py \
rag/graphrag/general/index.py \
test/unit_test/rag/graphrag/test_checkpoints.py
```
Result:
```text
Passed
```
```bash
uv run pytest test/unit_test/rag/graphrag/test_checkpoints.py
```
Result:
```text
4 passed
```
```bash
uv run pytest \
test/unit_test/rag/graphrag/test_phase_markers.py \
test/unit_test/rag/graphrag/test_graphrag_utils.py \
test/unit_test/rag/graphrag/test_checkpoints.py
```
Result:
```text
95 passed
```
```bash
git diff --check
```
Result:
```text
Passed
```
## Checklist
- [x] Implemented checkpoint/resume support for `extract_community`.
- [x] Implemented checkpoint/resume support for `resolve_entities`.
- [x] Avoided touching unrelated API behavior.
- [x] Added unit tests for the new checkpoint helper logic.
- [x] Verified Python syntax compilation.
- [x] Ran related GraphRAG unit tests successfully.
- [x] Ran `git diff --check`.
- [ ] Ran full project test suite.
---------
Co-authored-by: Wang Qi <wangq8@outlook.com>
### What problem does this PR solve?
Display intl `base_url` for Tongyi-Qianwen
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix: resolve issue where some models do not use modelInfo parameter
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
OceanBase could start without the `ragflow` tenant, so RAGFlow failed to
connect with `root@ragflow`. This PR adds a safe startup reconcile step
and documents the required host limits before using OceanBase.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Documentation Update
## Summary
The embedding branch of `verify_api_key` was missing `await` on
`asyncio.wait_for(...)`, so valid embedding-only providers always failed
API-key verification.
## Root cause
`arr, tc = asyncio.wait_for(...)` (no `await`) returns a coroutine;
unpacking it raises `TypeError: cannot unpack non-iterable coroutine`,
which the `except` swallows as a failure. The chat branch (`await
asyncio.wait_for(check_streamly())`) and rerank branch (`arr, tc = await
asyncio.wait_for(...)`) already `await` correctly.
## Fix
```diff
- arr, tc = asyncio.wait_for(
+ arr, tc = await asyncio.wait_for(
asyncio.to_thread(mdl.encode, ["Test if the api key is available"]),
timeout=timeout_seconds,
)
```
## Files changed
- `api/apps/services/provider_api_service.py`
## Verification
- `ruff check` — clean
- Fix mirrors the already-correct chat/rerank branches in the same
function. Local full pytest not run (heavy RAG deps); CI validates.
## Note
Implemented with LLM assistance (model: claude-opus-4-8).
Closes#15619
Co-authored-by: dearsishs <MCarter112116@outlook.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Summary
`SearchService.get_detail` crashed with `AttributeError` (HTTP 500) when
no matching row existed, because it called `.first().to_dict()` before
the `if not search` guard — making that guard dead code.
## Root cause
`.first()` returns `None` when the query matches nothing (deleted search
app, or joined `User` not `VALID`). `None.to_dict()` raises before the
guard runs.
## Fix
```diff
.first()
- .to_dict()
)
if not search:
return {}
- return search
+ return search.to_dict()
```
Guard the `None` first, then serialize — restoring the intended `{}`
"not found" return that every caller (`search_api`, `bot_api`,
`chat_api`, `dataset_api_service`) already handles.
## Files changed
- `api/db/services/search_service.py`
## Verification
- `ruff check` — clean
- Logic: `.first()` → `None` now hits `return {}` instead of
`None.to_dict()`. Local full pytest not run (heavy RAG deps); CI
validates.
## Note
Implemented with LLM assistance (model: claude-opus-4-8).
Closes#15621
Co-authored-by: dearsishs <MCarter112116@outlook.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Problem
`TestXiaomiNewModelWithCustomDefaultTransport` panics on Go 1.25:
```
panic: interface conversion: http.RoundTripper is models.roundTripperFunc, not *http.Transport
```
In Go 1.25, `http.DefaultTransport` is no longer `*http.Transport`, so
the unchecked type assertion in `NewXiaomiModel` panics when the test
replaces it with a `roundTripperFunc`.
## Fix
Use a safe type assertion with fallback to a new `http.Transport`,
matching the pattern already used in `modelscope.go`.
## Verification
```bash
go test -run TestXiaomiNewModelWithCustomDefaultTransport ./internal/entity/models/...
# PASS
```
Internal contributors only.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
### What problem does this PR solve?
`is_english()` in `rag/nlp/__init__.py` compiles a **single-character**
regex class and `fullmatch`es it against each item:
```python
pattern = re.compile(r"[`a-zA-Z0-9\s.,':;/\"?<>!\(\)\-]") # no quantifier
...
eng = sum(1 for t in texts if pattern.fullmatch(t.strip()))
```
For a **string** argument the text is first split into single characters
(`texts = list(texts)`), so each `fullmatch` sees one character and
works. But for a **list** argument each item is a whole multi-character
string, and `fullmatch` of a one-character pattern against a
multi-character string always fails — so `is_english()` returns `False`
for **any** list, regardless of content.
```python
is_english("This is English") # True (ok)
is_english(["The quick brown fox jumps.", "Hello world."]) # False (bug — should be True)
is_english(["这是中文。"]) # False (right answer, wrong reason)
```
Many call sites pass lists and were therefore silently always-`False`,
e.g.:
- `rag/llm/chat_model.py:1088`, `rag/llm/cv_model.py:168,1155` —
`is_english([ans])` when an answer is truncated at `max_tokens`, so an
English reply gets the Chinese "······由于长度的原因，回答被截断了，要继续吗？" continuation
suffix instead of the English one.
- `rag/app/book.py` — `remove_contents_table(...,
eng=is_english([...sections...]))`, so English books have their contents
table stripped in Chinese mode.
- `common/doc_store/es_conn_base.py:339`,
`rag/utils/opensearch_conn.py:733` — `is_english(txt.split())` in
highlight handling.
- plus `rag/app/qa.py`, `rag/flow/parser/utils.py`,
`common/doc_store/infinity_conn_base.py`.
### Fix
Add a `+` quantifier so an all-English multi-character item matches:
```python
pattern = re.compile(r"[`a-zA-Z0-9\s.,':;/\"?<>!\(\)\-]+")
```
The string path is unchanged (single characters still match) and
non-English lists still return `False`. Adds
`test/unit_test/rag/test_is_english.py`; the two list cases fail before
this change and pass after.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Used the Claude CLI while working on this.
### What problem does this PR solve?
Support model list for VolcEngine.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## What problem does this PR solve?
Go test files are never compiled in CI — only production binaries via
`go build`. This allowed a missing `"sort"` import in
`metadata_filter_test.go` to be merged without detection.
## Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
## Changes
- Add `go test -count=1 ./internal/...` step after Go build in CI
workflow
- Fix missing `"sort"` import in `metadata_filter_test.go` (pre-existing
compile error)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## Summary
Normalizes Qwen model-family names before reasoning extraction so
provider-prefixed Qwen models use the existing `<think>...</think>`
fallback.
## Summary
- keep MiniMax chat calls in non-streaming mode and streaming calls in
SSE mode
- make MiniMax model listing and connection checks use a bodyless GET
/v1/models
- add focused MiniMax request/response regression tests
### What problem does this PR solve?
**Verified from CLI**
```
RAGFlow(user)> chat with 'mimo-v2.5@test@xiaomi' message 'who r u'
Answer: Hello! I'm MiMo-v2.5, a large language model developed by Xiaomi's LLM Core Team. You can think of me as a friendly AI assistant ready to help you answer questions, have conversations, or work on creative tasks. My context window can handle up to 1 million tokens, so we can dive into pretty long discussions or documents if you'd like. What can I help you with today?
Time: 3.831830
RAGFlow(user)> stream chat with 'mimo-v2.5@test@xiaomi' message 'who r u'
Answer: there! I'm MiMo-v2.5, an AI assistant created by the Xiaomi LLM Core Team. I'm here to chat, help out, answer questions, or just have a friendly conversation. Think of me as a helpful buddy with a pretty big memory (1 million tokens worth!). What can I do for you today?😊
Time: 2.421630
RAGFlow(user)> think chat with 'mimo-v2.5@test@xiaomi' message 'who r u'
Thinking: The user is asking a simple question about who I am. According to my system prompt, I should:
- Identify myself as **MiMo-v2.5**
- State that I was developed by the **Xiaomi LLM Core Team**
- Answer in first person and be warm and conversational
Answer: Hey there! 👋
I'm **MiMo**, an AI assistant created by the **Xiaomi LLM Core Team**. Think of me as a friendly chat buddy who's here to help you with all sorts of questions and tasks!
I love having conversations, answering questions, brainstorming ideas, and helping people figure things out. Whether you want to chat, need help with something specific, or just want to explore ideas together — I'm here for it! 😊
What can I help you with today?
Time: 6.651589
RAGFlow(user)> tts with 'mimo-v2.5-tts@test@xiaomi' text 'hello? show yourself' play format 'wav' param '{"voice": "Chloe"}'
SUCCESS
RAGFlow(user)> asr with 'mimo-v2.5-asr@test@xiaomi' audio './internal/test.wav' param '{"language": "zh"}'
+------------------------------------------------------------------------------------------------------------------------+
| text |
+------------------------------------------------------------------------------------------------------------------------+
| 1 The examination and testimony of the experts enabled the commission to conclude that five shots may have been fired. |
+------------------------------------------------------------------------------------------------------------------------+
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
## Summary
- keep Moonshot chat calls in non-streaming mode and streaming calls in
SSE mode
- make Moonshot model listing and balance checks use bodyless GET
requests
- add focused Moonshot request/response regression tests
### What problem does this PR solve?
Fix LM-Studio provider connection verification so embedding checks await
the async wrapper correctly and log the full traceback on failures.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Add a waiting status to the messages on the chat page.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix: Resolve error when checking pipeline parsing result
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Table parser metadata aggregation previously only ran when
`table_column_mode` was set to `manual`. In auto mode (default), all
columns default to `"both"` role, meaning they should also be aggregated
into document-level metadata for UI/chat filters. Additionally, the task
snapshot could be stale — `table_column_names` are written to KB
`parser_config` during `chunk()` but the task may have been created
before that.
Changes:
- Renames `aggregate_table_manual_doc_metadata` →
`aggregate_table_doc_metadata`
- Supports both `"manual"` and `"auto"` `table_column_mode` (defaults to
`"auto"`)
- Reloads `table_column_names` from KB DB when missing from task
snapshot
- Removes the manual-only guard in `task_executor` and refactored
`post_processor`
- Updates all tests with new function name and adds auto mode test cases
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR adds `ModelMeta` implementations for four additional LLM/RAG
ecosystem platforms, building on the ModelMeta infrastructure introduced
in #15711.
Currently, only `Ollama` and `VolcEngine` have `ModelMeta` classes that
enable remote model list fetching. This PR extends that support to four
more platforms.
### Changes
Added four new `ModelMeta` subclasses in `rag/llm/model_meta.py`:
| Platform | `_FACTORY_NAME` | Has model list | Has full model info |
Approach |
|----------|-----------------|----------------|---------------------|----------|
| **Xinference** | `"Xinference"` | ✅ | ✅ | Parses `model_type` and
`context_length` from `/v1/models` response. Maps 6 model types
(LLM/embedding/rerank/image/TTS/speech2text). |
| **LocalAI** | `"LocalAI"` | ✅ | ✅ | Uses Ollama-compatible `GET
/api/tags` + `POST /api/show` endpoints. Returns capabilities
(completion/embedding/vision/tools/thinking) and
`general.context_length`. |
| **BaiduYiyan** | `"BaiduYiyan"` | ✅ | ✅ | Uses Qianfan SDK static
model catalog + `get_model_info()` for `max_input_tokens`. Returns 60
models (56 chat + 4 embedding) with real context lengths. |
| **Tencent Cloud** | `"Tencent Cloud"` | ❌ | ❌ | `NotImplementedError`
— uses SDK-based SID/SK HMAC signing, no model list REST API available.
|
All classes are automatically discovered and registered via the existing
`__init__.py` mechanism — no additional configuration needed.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Browser parsed sys.query from prompts but never called set_input_value,
so node_finished inputs displayed null in the agent orchestration run
log.
Additionally, Browser’s tenant-model path could trigger unsupported
structured-output modes (response_format/tool_choice) for some
OpenAI-compatible providers (notably DeepSeek thinking models), causing
step failures.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Fixes#15413
### What problem does this PR solve?
In **Settings → Model providers**, the *Available models* panel lets you
filter
providers by model type (All, LLM, Embedding, Rerank, TTS, ASR, VLM, …),
but the
filter tags gave no hint of how many providers fall under each type.
Users had to
click a tag to find out, and an empty category looked identical to a
populated one.
This PR adds a count to each filter tag in `AvailableModels`:
- The **All** tag shows the total number of providers currently listed.
- Each model-type tag shows how many providers offer that model type.
- Counts respect the active search term, so the badge always matches the
number of
cards shown once that tag is selected.
- Each provider is counted once per model type (deduplicated via a
`Set`), so a
provider that lists the same type more than once isn't double-counted.
Counts are rendered with `tabular-nums` for stable width and dimmed via
`opacity-60`
so they read as secondary to the label. No API changes; the existing
filter logic is
untouched — this is purely an additive UI affordance.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Follow-up to #15393. After #15393 fixed the OpenSearch `search()`
signature and
the doc-meta mapping, document metadata still renders as **"0 fields"**
for every
document on the OpenSearch backend (`DOC_ENGINE=opensearch`).
**Root cause.** `OSConnection.insert()` pops `id` out of the document
before
indexing:
meta_id = d_copy.pop("id", "") # id used as _id, then DROPPED from
_source
so the stored `_source` never contains an `id` field. But the doc-meta
read path
filters and sorts on that field:
- `DocMetadataService.get_metadata_for_documents()` builds
`condition = {"kb_id": kb_id, "id": doc_ids}` -> `OSConnection.search()`
emits
`Q("terms", id=doc_ids)` (a term query on the `id` field), and
- `_search_metadata()` sorts with `order_by.asc("id")`.
With `id` absent from `_source`, the terms filter matches nothing, so
`get_metadata_for_documents()` returns an empty map and the UI shows "0
fields"
-- even though the metadata was written correctly (it is visible via a
kb_id-only query).
`ESConnection.insert()` already keeps `id` (`d_copy.get("id", "")`) with
the
comment *"also keep 'id' as a regular field for sorting"*. This is a
plain
OpenSearch-only divergence (`pop()` vs `get()`).
### Fix
Mirror Elasticsearch: use `get("id")` instead of `pop("id")` so `id`
survives in
`_source`. The doc-meta mapping already declares `id` as `keyword`, so
the field
is searchable/sortable once populated.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Affected backends
OpenSearch only. Elasticsearch already keeps `id`; Infinity / OceanBase
unaffected.
### How to reproduce
1. `DOC_ENGINE=opensearch`, create a KB, upload/parse a document, set
metadata.
2. Open the document list -> every document shows "0 fields" (the
metadata exists
in the `ragflow_doc_meta_*` index but its `_source` has no `id` field).
### Risk & backward compatibility
`insert()` is shared with the main chunk index; keeping `id` in
`_source` brings
OpenSearch in line with Elasticsearch (which already does this), so it
is parity,
not new behavior. No default / ES / Infinity / OceanBase behavior
change.
Note: affects new inserts only. Existing `ragflow_doc_meta_*` indices
created
before this change have no `id` in `_source`; re-sync metadata, or
backfill once
with `_update_by_query` (`ctx._source.id = ctx._id`).
### Test plan
- [ ] OpenSearch: after the fix the document list shows correct metadata
field
counts (not "0 fields"); metadata filter/sort by id works.
- [ ] Elasticsearch regression: unchanged.
### What problem does this PR solve?
`RAGFlowExcelParser.html()` iterates `(len(rows) - 1) // chunk_rows + 1`
times. `rows[0]` is the header, so `len(rows) - 1` is the data-row
count. When that count is an exact multiple of `chunk_rows`, the `+ 1`
over-counts by one: the final iteration's data slice is empty, but the
header row is still appended — producing a chunk that contains only the
table header and no data.
This is reachable via `rag/app/naive.py` (`html4excel`, `chunk_rows=12`)
and `rag/app/one.py`. A sheet with 12/24/36… data rows (or 256/512… with
the default `chunk_rows=256`) produces an extra
`<table><caption>…</caption><tr><th>…</th></tr></table>` chunk. It is
non-empty, so it passes the `if _` filter and gets indexed as a real
(empty) chunk.
| data rows (chunk_rows=12) | before | after |
|---|---|---|
| 12 | 2 chunks (1 header-only) | 1 |
| 24 | 3 chunks (1 header-only) | 2 |
| 13 | 2 (unchanged) | 2 |
### Fix
Iterate `ceil(n_data / chunk_rows)` times instead of `n_data //
chunk_rows + 1`. Adds
`test/unit_test/deepdoc/parser/test_excel_parser.py`; the
header-only-chunk cases fail before this change and pass after.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Used the Claude CLI while working on this.
## Summary
Closes#15720
`FulltextQueryer.paragraph` normalized its `content_tks` token string
with `[c.strip() for c in content_tks.strip() ...]`, which iterates the
string **character by character** — `"machine learning model"` becomes
20 single characters instead of 3 tokens. Those single chars are fed to
`tw.weights(..., preprocess=False)`, producing meaningless term weights
and a garbage `MatchTextExpr`.
`paragraph()` backs `Dealer.tag_content` (the KB auto-tagging feature),
so tag retrieval/scoring is silently broken for tag-enabled knowledge
bases. Every other method in this file tokenizes with `.split()` — this
is a `.strip()`-vs-`.split()` typo.
## Change
- `rag/nlp/query.py` — change `content_tks.strip()` to
`content_tks.split()` in the `paragraph` token-normalization line.
## Why it's safe
- The caller passes a space-separated token string; `.split()` recovers
the real tokens, matching the contract of `tw.weights` and the
`.split()` tokenization used by the sibling methods (`similarity`,
`question`).
- No behavior depends on the per-character expansion.
## Verification
- `python -m py_compile rag/nlp/query.py` — OK.
- Demonstrated: `"machine learning model"` → 20 single-character entries
before, 3 real tokens after. No test references `paragraph`.
Co-authored-by: seekmistar01 <seekmistar01@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
## What problem does this PR solve?
Implements `FetchChunkVectors` — the infrastructure needed to hydrate
chunk embedding vectors on demand. This is a prerequisite for
`insert_citations` (citation insertion in the `searchbots/ask`
endpoint), matching the Python `Dealer.fetch_chunk_vectors` pattern.
Without this, citation insertion cannot compute answer-vs-chunk vector
similarity.
## Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Changes
### New Function
- `FetchChunkVectors(engine, chunkIDs, tenantIDs, kbIDs, dim)` — fetches
embedding vectors for a set of chunk IDs
- Consumer-side `vectorFetcher` interface with only `Search` + `GetType`
methods
- Both `*elasticsearchEngine` and `*infinityEngine` implicitly satisfy
the interface
### Engine Behavior
- **ES**: queries by chunk ID list via `Search` with filter `{"id":
chunkIDs}`, parses tab-separated `q_N_vec` string format
- **Infinity / OceanBase**: skips the round-trip (vectors already
shipped with chunks)
- **Degrades gracefully**: engine errors return zero vectors — citation
insertion will use placeholders instead of failing
### Vector Parsing
- Handles ES tab-separated string format (`"0.1\t0.2\t0.3"`)
- Handles `[]float64` and `[]interface{}` formats
- Returns zero vector for wrong-dimension or unparseable input
### Bug Fix
- `metadata_filter_test.go`: add missing `"sort"` import (pre-existing
build break)
### Tests
- 12 unit tests: empty input, Infinity/OceanBase skip, ES string vector,
ES float slice, ES interface slice, search error degradation, missing
chunk → zero, wrong dimension → zero, parse edge cases
## Files Changed
| File | Change |
|------|--------|
| `internal/service/chunk_vector.go` | New — FetchChunkVectors + parse
helpers |
| `internal/service/chunk_vector_test.go` | New — 12 tests |
| `internal/service/metadata_filter_test.go` | Fix missing `"sort"`
import |
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
### What problem does this PR solve?
Refine the stream parsing for `<think>` / `</think>` so MiniMax and
DeepSeek-style chunking both flush in the right order without mixing
think and answer buffers.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
feat：Unify the 'Add Model Provider' modal
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
As Title
Codes were tested by Postman
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
