# feat: Add Generic REST API Connector
## What problem does this PR solve?
RAGFlow supports many specific data source connectors (MySQL, Slack,
Google Drive, etc.), but there was no way to connect an arbitrary REST
API as a data source. Users with custom or third-party APIs had to write
a new connector class for each one.
This PR adds a **generic, configuration-driven REST API connector** that
lets users connect any REST API as a data source entirely through the UI
— no code changes needed per API.
---
## Features
### Core Connector (`common/data_source/rest_api_connector.py`)
- Implements `LoadConnector` and `PollConnector` interfaces for full and
incremental sync
- **Configurable authentication:** None, API Key (custom header), Bearer
Token, Basic Auth
- **Pluggable pagination:** Page-based, Offset-based, Cursor-based, or
None
- Smart page-size inference from user's query parameters to avoid
duplicate/conflicting params
- Configurable request delay between pages to prevent API rate limiting
- Auto-detection of the items array in JSON responses (`items`,
`results`, `data`, `records`, or first list found)
- **Advanced field mapping** with dot-notation (`country.name`), array
wildcards (`newsType[*].name`), type hints, and default values
- Optional content template rendering (`"Title: {title}\nBody: {body}"`)
- HTML stripping for content fields
- Stable document IDs via `hash128` from a configurable ID field or
auto-generated from item content
- Pydantic configuration schema with automatic coercion of UI string
inputs to dicts/lists
### Backend Registration (`rag/svr/sync_data_source.py`,
`common/constants.py`, `common/data_source/config.py`)
- `REST_API` sync class wired into RAGFlow's `func_factory`
- Full sync (`load_from_state`) and incremental polling (`poll_source`)
support
- Credentials and config passed from task to connector following
existing patterns (MySQL, SeaFile, etc.)
### Test Connection Endpoint (`api/apps/connector_app.py`)
- `POST /v1/connector/<id>/test` validates config schema,
authentication, and API connectivity without triggering a sync
- Clear error messages for auth failures vs. config issues
### Frontend UI (`web/src/pages/user-setting/data-source/constant/`)
- **Postman-style configuration:** Base URL, Query Parameters (key=value
per line), Auth, Content Fields, Metadata Fields, Pagination Type
- Auth-type-aware form: fields for API key header/value, Bearer token,
or Basic username/password appear only when relevant
- **Advanced Settings** toggle for: Custom Headers, Max Pages, Request
Delay, Poll Timestamp Field, Request Body (POST)
- Connector icon (SVG) and i18n strings (English)
- **"Test Connection"** button to validate before syncing
---
## Controls & Safety
- Configurable max pages safety cap (default: 1000, adjustable in UI)
- Configurable request delay between pages (default: 0.5s, adjustable in
UI)
- Auth errors (401/403) fail immediately without retries; transient
errors retry with exponential backoff
- Diagnostic logging: auth setup confirmation, request details on
failure, content field extraction status
---
## Type of change
- [x] New Feature (non-breaking change which adds functionality)
##Visual Screenshots of Features
<img width="482" height="510" alt="Screenshot 2026-03-11 at 5 19 52 PM"
src="https://github.com/user-attachments/assets/dcb7ab4a-1622-44f3-bb02-d6f0527314c4"
/>
(Connector can be configured within the external data sources tab)
Configuration Parameters:
<img width="661" height="682" alt="Screenshot 2026-03-11 at 5 20 46 PM"
src="https://github.com/user-attachments/assets/5e154e71-4ab5-4872-bfb2-04f02b73c18a"
/>
<img width="661" height="682" alt="Screenshot 2026-03-11 at 5 20 54 PM"
src="https://github.com/user-attachments/assets/00cb14b7-0bcf-4b94-9d71-34e93369ecb2"
/>
Connection can be tested before attaching to dataset:
<img width="981" height="681" alt="Screenshot 2026-03-11 at 5 21 40 PM"
src="https://github.com/user-attachments/assets/aaa6eeeb-89a7-4349-bc34-2423bf8be9ee"
/>
Ingestion tested with API connector (works perfectly fine):
<img width="1062" height="705" alt="Screenshot 2026-03-11 at 5 22 30 PM"
src="https://github.com/user-attachments/assets/afcd0d58-cadd-4152-badc-d2f14d96fbec"
/>
Search & Retrieval works as well with metadata flow:
<img width="1062" height="705" alt="Screenshot 2026-03-11 at 5 23 05 PM"
src="https://github.com/user-attachments/assets/d41ee935-dcf7-4456-b317-22a76ca032c0"
/>
---------
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
### What problem does this PR solve?
add new testing suite for the new restful api endpoints meant to replace
http and web api tests
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Other (please describe): test
## Problem
When parsing DOCX files with many tables, DeepDOC generates chunks
containing only empty HTML table tags, such as:
```html
<table><tr><td></td></tr><tr><td></td></tr><tr><td></td></tr><tr><td></td></tr></table>
```
After the regex cleanup at `task_executor.py:584`, this becomes `" "`
(whitespace only).
The guard at line 585 (`if not c`) only catches empty strings `""`, but
whitespace strings are truthy in Python and pass through. When sent to
Zhipu `embedding-3` API, it rejects them with error 1213:
`未正常接收到prompt参数`.
## Root Cause
```python
c = re.sub(r"</?(table|td|caption|tr|th)( [^<>]{0,12})?>", " ", c)
if not c: # ← only catches "", not " " / "\n" / "\t"
c = "None"
```
Verified with Zhipu `embedding-3`:
| Input | Result |
|---|---|
| `""` | error 1213 |
| `" "` | error 1213 |
| `"\n"` | error 1213 |
| `"None"` | OK |
## Fix
```diff
- if not c:
+ if not c.strip():
c = "None"
```
## Testing
Reproduced with a 678KB DOCX file (166 tables, 270 chunks). Chunk #89 is
the empty table above. After fix, `"None"` is sent instead and embedding
succeeds.
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
What problem does this PR solve?
In rag/app/audio.py, the supported audio extensions list contains
duplicate entries: .wav appears twice (positions 3 and 5) and .aac
appears twice (positions 6 and 14). While this does not affect runtime
behavior, it is redundant and makes the code harder to maintain.
This PR removes the duplicate entries to keep the list clean and
consistent.
Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Closes#14674.
This PR improves RAPTOR configuration and tree construction while
preserving the existing RAPTOR behavior as the default.
RAPTOR currently builds summary layers with the original UMAP + GMM
clustering path. This PR keeps that default path, and adds:
- A hidden backend tree-builder option:
- `tree_builder="raptor"`: default, existing RAPTOR behavior.
- `tree_builder="psi"`: rank-aware Psi-style tree builder using original
embedding-space cosine ranking.
- A user-facing clustering method option for the default RAPTOR builder:
- `clustering_method="gmm"`: existing default.
- `clustering_method="ahc"`: agglomerative hierarchical clustering path.
- A RAPTOR UI setting for `Clustering method` and `Max cluster`.
### What changed
#### Backend
- Added `tree_builder` support for RAPTOR/Psi.
- Added `clustering_method` support for GMM/AHC.
- Kept existing RAPTOR + GMM as the default.
- Added Psi tree building from original-space cosine similarity.
- Added bucketed Psi building controls for large inputs:
- `raptor.ext.psi_exact_max_leaves`
- `raptor.ext.psi_bucket_size`
- Added method-aware RAPTOR summary metadata using existing
`extra.raptor_method`.
- Avoided adding a dedicated DB schema field for experimental method
tracking.
- Added cleanup/migration logic to avoid mixing stale RAPTOR summary
trees.
- Added defensive checks for Psi tree construction and summary failures.
#### Frontend/UI
- Added `Clustering method` in RAPTOR settings with `GMM` and `AHC`.
- Added/kept `Max cluster` in RAPTOR settings.
- Enlarged max cluster UI limit to `1024`, matching backend validation.
- Kept AHC editable even when a RAPTOR task has already finished.
- Fixed the UI save payload so `clustering_method` and `tree_builder`
are serialized through `parser_config.raptor.ext`, avoiding backend
validation errors for extra top-level RAPTOR fields.
Example saved RAPTOR config:
```json
{
"raptor": {
"max_cluster": 317,
"ext": {
"clustering_method": "ahc",
"tree_builder": "raptor"
}
}
}
Co-authored-by: CaptainTimon <CaptainTimon@users.noreply.github.com>
### What problem does this PR solve?
Fixes#14570. On OpenSearch backends (`DOC_ENGINE=opensearch`) every
document-metadata write failed with `'OSConnection' object has no
attribute 'create_doc_meta_idx'`, so both `PATCH
/api/v1/datasets/{ds}/documents/{doc}` with `meta_fields` and `POST
/api/v1/datasets/{ds}/metadata/update` were unusable while every other
document operation (retrieval, parsing, name update, chunk management)
worked correctly on the same OpenSearch cluster.
The bug runs deeper than the missing method name in the error message
suggests. `DocMetadataService` also reached into
`settings.docStoreConn.es.*` directly for the index refresh, the
scripted partial update, and the count call, which means that even after
adding `create_doc_meta_idx` to `OSConnection` the very next call in the
same metadata flow would still raise `AttributeError` because
`OSConnection` exposes `self.os` rather than `self.es`. Fixing only the
reported symptom would have moved the failure one line down without
restoring the feature.
This PR adds a uniform document-metadata dispatch surface to both
connection classes so they present the same abstract API, and routes the
service layer through that surface via `getattr` guards instead of
poking at backend-specific attributes. The four new methods on
`OSConnection` and `ESConnectionBase` are `create_doc_meta_idx`,
`refresh_idx`, `count_idx`, and `replace_meta_fields`.
`OSConnection.create_doc_meta_idx` reuses the existing
`conf/doc_meta_es_mapping.json` schema in the OpenSearch `body=` form
because OpenSearch and Elasticsearch share the same index-creation
payload, and `replace_meta_fields` emits a full scripted assignment
(`ctx._source.meta_fields = params.meta_fields`) on both backends so
removed keys actually disappear instead of being preserved by deep-merge
semantics.
The `getattr`-guarded dispatch in `DocMetadataService` keeps the
existing fall-through paths intact for Infinity and OceanBase, which
continue to rely on their search-based count fallback and on the
delete-then-insert metadata replacement they used before, so this change
is strictly additive for those two backends.
Verification: `pytest
test/unit_test/rag/utils/test_opensearch_doc_meta.py` runs 16 new unit
tests that pass locally and pin the `OSConnection` dispatch surface, the
`create_doc_meta_idx` short-circuit when the index already exists, the
mapping-file payload routing, the `IndicesClient.create` failure path,
the `refresh_idx` and `count_idx` success and error sentinels, and the
full-assignment script emitted by `replace_meta_fields`. The test module
stubs `common.settings` and `rag.nlp` at import time so the suite runs
without the heavy backend SDKs that the rest of the repository pulls in
transitively.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: tmimmanuel <tmimmanuel@users.noreply.github.com>
### What problem does this PR solve?
The document parse status was set to DONE before the document chunks
were actually retrievable from Elasticsearch/Opensearch because it did
not wait for the index refresh. This meant that it was possible that the
document parse status returned by the API was DONE but when trying to
retrieve chunks there were none. Since the index refreshes every 1
second this was quite likely to happen when wait for document parsing by
polling with a short interval and then immediately trying to retrieve
chunks once the status was DONE.
I fixed this bug and added a test case that would have caught it.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
pending_cell_images should be scoped by sheet
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
GraphRAG feature - Part 1 - add spacy to extract entity and relation
<img width="1621" height="1288" alt="image"
src="https://github.com/user-attachments/assets/aadeddad-94da-46c6-adad-9c3784181f61"
/>
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Summary
- Wrap the `ThreadPoolExecutor` instances in `FileService.parse_docs`
and `FileService.get_files` with `with ... as exe:` blocks for
deterministic cleanup
- Replace the `concurrent.futures.ThreadPoolExecutor` in
`do_handle_task` with `asyncio.create_task(asyncio.to_thread(build_TOC,
...))`, preserving the existing parallelism with chunk insertion while
leveraging the surrounding async context
- Drop the now-unused `import concurrent` and the
`executor.shutdown(wait=False)` call in the `finally` block
Closes#14622.
No behavioral change, no public API change. Net diff: ~19 insertions /
25 deletions across two files.
## Test plan
- [ ] `uv run ruff check api/db/services/file_service.py
rag/svr/task_executor.py` passes
- [ ] Upload a multi-file batch through the chat/file endpoint and
confirm `FileService.parse_docs` still returns combined parsed text
- [ ] Trigger `FileService.get_files` via the chat reference flow with a
mix of image and non-image files; verify both `raw=True` and `raw=False`
paths return correctly
- [ ] Run a `naive`-parser document task with `toc_extraction: true` and
confirm the TOC chunk is generated and inserted exactly as before
- [ ] Run a `naive`-parser document task with `toc_extraction: false`
and confirm the path with `toc_thread = None` is unaffected
- [ ] Cancel a running task to exercise the `finally` block and confirm
cleanup still works without the executor shutdown call
---------
Co-authored-by: web-dev0521 <jasonpette1783@gmail.com>
Co-authored-by: Wang Qi <wangq8@outlook.com>
## Summary
This PR fixes the `message_fit_in()` truncation bug reported in #13607.
Changes:
- fix the user-message truncation branch to reserve room for the system
prompt token budget
- guard the zero-token edge case to avoid dividing by zero in the
truncation ratio check
- add focused regression tests covering both the user-dominant
truncation path and the zero-token boundary case
## Validation
```bash
pytest -q --noconftest test/unit_test/rag/prompts/test_generator_message_fit_in.py
```
Result: `2 passed`
Closes#13607
## Summary
This PR fully addresses all CodeRabbit review feedback and enhances the
robustness of the reranking module with 100% backward compatibility.
## Key Fixes
1. Fixed JinaRerank hardcoded base_url to support subclass endpoint
overrides
2. Corrected GPUStackRerank exception handling to use proper requests
exceptions and preserve stack traces
3. Added 30s timeout to all API calls to prevent service hanging
4. Added empty input validation for all rerank providers
5. Replaced direct dict key access with .get() to eliminate KeyError
crashes
6. Fixed _normalize_rank edge case for empty arrays
7. Implemented missing functionality for Ai302Rerank
8. Standardized type hints and fixed typo issues
## Compatibility
- No breaking changes to any existing functionality
- All rerank providers work as originally intended
- Fully compatible with existing configurations and workflows
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
## What
Widen the keyword delimiter in `rag/svr/task_executor.py`:
both `build_chunks` (LLM `keyword_extraction` cache parsing) and
`run_dataflow` (chunk-level `keywords` ingestion) now split on
`, ， ; ； 、 \r \n` instead of only ASCII comma.
## Why
`rag/prompts/keyword_prompt.md` instructs the LLM:
> The keywords are delimited by ENGLISH COMMA.
In practice, Chinese-leaning models (Qwen / Tongyi-Qianwen, GLM,
etc.) frequently ignore this instruction when the source content is
Chinese and emit Chinese commas (`，`) instead. Result:
`cached.split(",")` sees the full LLM output as a *single* keyword.
Repro: `auto_keywords>=4` + Chinese docs + `qwen-plus@Tongyi-Qianwen`.
We observed entries in `important_kwd` like
`"功能介绍，配置说明，参数详解，问题排查"` — one bucket instead of four.
## Impact
- Silent data-quality bug; no exception thrown.
- BM25 `important_kwd^30` boost effectively stops firing — the
indexed term is the whole list, never matches user query tokens.
- Any downstream aggregating `important_kwd` (tagging, analytics,
candidate-keyword review UIs) sees garbage.
## Compatibility
- Pure widening of the splitter; ASCII-comma-only outputs continue
to work identically.
- No schema / API change.
## Test plan
Manually verified against `qwen-plus@Tongyi-Qianwen` with
`auto_keywords=10` on Chinese .txt files:
- Before: `important_kwd` contains one element per chunk that is the
full LLM string with `，`-separated phrases inside.
- After: `important_kwd` contains N elements, one per phrase, as the
LLM intended.
### What problem does this PR solve?
`retrieval_by_children()` in `rag/nlp/search.py` crashes with a
`TypeError: 'NoneType' object is not subscriptable` when a parent
("mom") chunk referenced by child chunks is missing from the index.
This happens when the index is in an inconsistent state — for example
after a partial re-index, a document deletion that didn't clean up all
children, or a race condition during ingestion. `dataStore.get()`
returns `None` for the missing parent, and the subsequent access to
`chunk["content_with_weight"]` raises a `TypeError`.
**Stack trace:**
```
TypeError: 'NoneType' object is not subscriptable
File "rag/nlp/search.py", line 792, in retrieval_by_children
"content_with_weight": chunk["content_with_weight"],
```
### Type of change
- [x] Bug Fix
### Fix
When `dataStore.get()` returns `None` for a parent chunk, fall back to
using the child chunks directly and continue processing the remaining
parents. This preserves retrieval results for all other chunks rather
than aborting the entire query with an exception.
```python
chunk = self.dataStore.get(id, idx_nms[0], [ck["kb_id"] for ck in cks])
if chunk is None:
chunks.extend(cks)
continue
```
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
Multiple `requests.post()` calls across the LLM integration layer lack a
`timeout` parameter. Without a timeout, a single unresponsive upstream
service can block the calling thread **indefinitely**, eventually
exhausting the thread pool and degrading the entire system.
This is a well-known issue — Python's `requests` library defaults to
`timeout=None` (infinite wait), and [the library docs explicitly
recommend](https://requests.readthedocs.io/en/latest/user/advanced/#timeouts)
always setting a timeout.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Change
Added `timeout` to all `requests.post()` calls missing it:
| File | Calls fixed | Timeout |
|------|-------------|---------|
| `rag/llm/rerank_model.py` | 9 | 30s |
| `rag/llm/embedding_model.py` | 8 | 30s |
| `rag/llm/cv_model.py` | 3 | 60s |
| `rag/llm/tts_model.py` | 2 | 60s |
| `rag/llm/sequence2txt_model.py` | 2 | 60s |
Embedding/rerank calls use 30s (lightweight API calls). Vision, TTS, and
audio transcription use 60s (heavier workloads with file uploads).
Note: other files in the codebase (e.g. `check_minio_alive`,
`check_ragflow_server_alive`) already use `timeout=10`, so this PR
brings the LLM layer in line with existing practice.
Signed-off-by: Ricardo-M-L <Sibyl_Hartmanbnb@webname.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
## Summary
- `CvModel["Bedrock"]` was absent from `rag/llm/cv_model.py`, causing
`model_instance()` to return `None` when a Bedrock model was used as a
PDF parser — even after correct model resolution.
- This PR adds `BedrockCV`, enabling Bedrock vision models (e.g.
`amazon.nova-pro-v1:0`, `anthropic.claude-3-5-sonnet`) to be used as PDF
parsers.
## What problem does this PR solve?
When a Bedrock model is selected as the PDF parser in a knowledge base,
ingestion failed with:
```
'LiteLLMBase' object has no attribute 'describe_with_prompt'
```
The root cause: `LiteLLMBase` (the Bedrock chat implementation) was the
only registered handler for the Bedrock factory. It does not implement
`describe_with_prompt`. `CvModel` had no Bedrock entry, so
`model_instance()` returned `None` for `image2text` requests.
## Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Changes
**`rag/llm/cv_model.py`**
Adds `BedrockCV(Base)` with `_FACTORY_NAME = "Bedrock"`:
- Uses `litellm.completion` with the `bedrock/` prefix (consistent with
`LiteLLMBase`)
- Parses AWS credentials from the JSON key assembled by `add_llm`
(`auth_mode`, `bedrock_ak`, `bedrock_sk`, `bedrock_region`,
`aws_role_arn`)
- Supports three auth modes: `access_key_secret`, `iam_role` (via STS
`assume_role`), and default credential chain (IRSA, instance profile)
- Implements `describe_with_prompt` and `describe`
## Test plan
- [ ] Configure a Bedrock vision model (e.g. `amazon.nova-pro-v1:0`)
with valid AWS credentials
- [ ] Select it as PDF parser in a knowledge base
- [ ] Verify ingestion of a PDF document completes without errors
- [ ] Verify `CvModel["Bedrock"]` resolves to `BedrockCV`
🤖 Generated with [Claude Code](https://claude.ai/claude-code)
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
The table file parser (CSV/Excel) currently treats all columns
identically — every column is both vectorized (embedded in chunk text)
and stored as filterable metadata. There's no way for users to control
which columns should be searchable by semantic meaning versus which
should only be filterable attributes.
For example, when ingesting a news articles CSV with columns like title,
content, country, category, source, etc., the embedding includes
metadata fields like country: Brazil and source: Reuters in the chunk
text, which dilutes the semantic quality of the embedding without adding
retrieval value.
The RDBMS connector (MySQL/PostgreSQL) already supports content_columns
/ metadata_columns, but this capability was missing for file-based table
ingestion.
This PR adds column-level control (vectorize / metadata / both) for the
table file parser, following RAGFlow's existing patterns.
Backward compatible: Datasets without table_column_roles or with
table_column_mode: auto behave exactly as before (all columns = both).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
HuggingfaceRerank.post() unconditionally prepends `http://` to base_url,
which already contains a protocol. This creates invalid URLs like
http://http://127.0.0.1:8080/rerank, breaking all requests. The fix
normalizes URL handling to match the rest of the codebase, removing
redunant `http://`.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Related Issues
- #7318
- #7796
---------
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
### What problem does this PR solve?
S3-family connector syncs currently re-download every in-window object
just so we can compute `xxhash128(blob)` and compare against
`Document.content_hash`. Anything that bumps `LastModified` without
changing bytes (`aws s3 cp` touches, bucket re-encryption, etc.) pays
full bandwidth and re-parses files that didn't actually change. #14628
covers the broader incremental-ingestion redesign; this PR is the first
slice.
The fix is a pre-listing short-circuit. `BlobStorageConnector` (S3 / R2
/ GCS / OCI / S3-compat) now implements a new `FingerprintConnector`
interface: `list_keys()` paginates `list_objects_v2` and yields
`KeyRecord(key, fingerprint)` where `fingerprint = xxhash128(ETag)`. The
orchestrator joins those against the connector's existing `{doc_id:
content_hash}` map and only calls `get_value(key)` when the fingerprint
differs. Unchanged keys are skipped entirely — no `GetObject`, no
re-parse.
No DDL. xxhash128(ETag) is 32 hex chars and reuses the existing
`Document.content_hash` column per @yingfeng's suggestion; the connector
decides at listing time whether to populate it. Local uploads and
connectors that don't opt in fall through to the existing post-download
`xxhash128(blob)` path with no behavior change.
This is PR-1 of a 4-PR series — full design lives on #14628. Subsequent
PRs extend tier 1 to local FS / WebDAV / Dropbox / Seafile / RDBMS
(PR-2), wire up tier 2 cursor connectors with `SyncLogs.next_checkpoint`
(PR-3), and unify deletion via `KeyRecord(deleted=True)` reconciliation
(PR-4). Holding those back keeps this PR additive and reviewable on its
own.
#### Files touched
- `common/data_source/models.py` — new `KeyRecord`; optional
`fingerprint` on `Document`
- `common/data_source/interfaces.py` — `IncrementalCapability` enum,
`FingerprintConnector` ABC
- `common/data_source/blob_connector.py` — `BlobStorageConnector`
implements `FingerprintConnector`; per-object download factored into
`_build_document_from_obj()` so `_yield_blob_objects`, `list_keys`,
`get_value` all share it
- `rag/svr/sync_data_source.py` —
`_BlobLikeBase._fingerprint_filtered_generator` does the bypass loop;
`_run_task_logic` plumbs `doc.fingerprint` into the upload dict
- `api/db/services/document_service.py` —
`list_id_content_hash_map_by_kb_and_source_type()` helper
- `api/db/services/connector_service.py` + `file_service.py` —
fingerprint flows through `duplicate_and_parse → upload_document` and
lands in `content_hash`
- `test/unit_test/common/test_blob_connector_fingerprint.py` — 14 tests
covering ETag normalization (single-part, multipart, quoted, empty),
`list_keys()` not calling `GetObject`, `get_value()` materializing with
fingerprint, deterministic/stable fingerprints, and the bypass loop
asserting `GetObject` is *not* called on a match
#### Worth flagging for review
Old `_BlobLikeBase._generate` called `poll_source(start, now)` with a
`LastModified` window when `poll_range_start` was set. New code uses
`_fingerprint_filtered_generator` (full bucket listing + fingerprint
compare) outside of explicit `reindex=1`. Strictly better for
unchanged-bucket cases since it skips `GetObject`, but it does mean
every sync now does a full `list_objects_v2` paginate. Should still be
cheap for most buckets — flagging in case anyone has a very large bucket
where the time-window filter was meaningful.
On migration: existing rows have `content_hash = xxhash128(blob)` from
the old code. The first sync after this lands sees ETag-derived
fingerprints that don't match, re-fetches every object once, and writes
the new fingerprint. From the second sync onward the bypass works as
expected. "Slow day one, fast every day after." A `fingerprint_backfill:
trust` opt-out is sketched in the design doc but not in this PR.
#### Test plan
- [x] `uv run ruff check` — clean on all 8 touched files
- [x] `uv run pytest
test/unit_test/common/test_blob_connector_fingerprint.py -v` — 14 passed
- [x] Broader unit-test suite — no regressions in anything I touched
- [ ] Manual smoke against a real S3 bucket — configure a connector, run
sync twice, expect the second sync to log `bypassed=N, fetched=0` and no
`GetObject` calls in CloudTrail / bucket access logs
- [ ] Manual smoke with `reindex=1` — confirm the full re-download path
still works
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Update mapping.json to treat id as a keyword.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What
19 methods across `rag/llm/chat_model.py` and `rag/llm/cv_model.py`
declare `gen_conf={}` (or `gen_conf: dict = {}`) as a parameter default
and then mutate `gen_conf` in place — typically `del
gen_conf["max_tokens"]`, `gen_conf["penalty_score"] = ...`, or
`gen_conf.pop(...)` as part of provider-specific normalization.
### The two bugs in this pattern
**1. Mutable default argument (Python footgun).** Python evaluates
default values **once** at function-definition time, so the single `{}`
dict is *shared* across every caller that doesn't pass `gen_conf`. The
first such call's mutations leak into the default seen by every
subsequent call.
```python
# Before
def chat_streamly(self, system, history, gen_conf={}, **kwargs):
if "max_tokens" in gen_conf:
del gen_conf["max_tokens"] # mutates the SHARED default dict
...
```
After call N with `max_tokens` set, call N+1 that omits `gen_conf` no
longer sees `max_tokens` — even though the caller never touched it.
**2. Caller-dict pollution.** When the caller *does* pass a `gen_conf`
dict, the same in-place mutations modify the caller's dict. A reused
`gen_conf` (very common for chat-loop callers that build the config once
and pass it on every turn) silently loses `max_tokens`,
`presence_penalty`, etc. after the first round.
### The fix
In every affected method:
- Change `gen_conf={}` (or `gen_conf: dict = {}`) → `gen_conf=None`.
- Add `gen_conf = dict(gen_conf or {})` as the first statement of the
body so all subsequent mutations operate on a fresh local copy.
```python
# After
def chat_streamly(self, system, history, gen_conf=None, **kwargs):
gen_conf = dict(gen_conf or {})
if "max_tokens" in gen_conf:
del gen_conf["max_tokens"] # local copy — safe
...
```
This is byte-for-byte identical provider-side behavior for callers that
already pass a fresh `gen_conf` per call. The new `dict(...)` copy is
O(small constant) per call.
### Files changed
- `rag/llm/chat_model.py` — 17 methods
- `rag/llm/cv_model.py` — 2 methods
### Tests
Adds `test/unit_test/rag/llm/test_gen_conf_no_mutable_default.py` — an
`ast`-based regression guard that walks both modules and asserts no
parameter named `gen_conf` ever has a mutable literal (`{}` or `[]`) as
its default. The test caught **five additional `gen_conf: dict = {}`
sites** that an initial `gen_conf={}` text grep had missed (annotated
parameters with whitespace), and would fail again if the pattern is ever
reintroduced.
```
$ pytest test/unit_test/rag/llm/test_gen_conf_no_mutable_default.py -v
============================== 3 passed in 0.04s ===============================
```
`ruff check` passes on all touched files.
### Notes
- This PR is intentionally focused on **just** the `gen_conf` default +
copy fix. There's a related (but separate) `history.insert(0, ...)`
pattern in the same files that mutates the caller's history list in 12
places — left for a follow-up so this PR stays mechanical and easy to
review.
### Latest revision (`700bb54a7`) — addresses CodeRabbit review
- Type annotation: `gen_conf: dict = None` → `gen_conf: dict | None =
None` (5 occurrences in `chat_model.py`). The old annotation was a
static-checker mismatch since `None` isn't a `dict`.
- Regression test: the AST check accessed `default.keys` directly.
`ast.List` has no `.keys` attribute — a future `gen_conf=[]` would crash
with `AttributeError` instead of being caught. Use `getattr` for both
`.keys` (Dict) and `.elts` (List). Manually verified the updated check
correctly catches both `gen_conf={}` and `gen_conf=[]` while ignoring
`gen_conf=None` and non-empty literals.
---------
Co-authored-by: Ricardo <ricardo@example.com>
## Summary
- When KB retrieval fails (e.g. ES `AssertionError` on empty
`index_names`), `kbinfos` falls back to a dict without a `total` key
- `_async_update_chunk_info` then iterates over `chunk_info.keys()`
(which includes `total`) and tries `kbinfos['total']`, raising a
`KeyError`
- This error surfaces when using Tavily web retrieval in a chat with no
knowledge base attached
## Changes
- Add `'total': 0` to all default `kbinfos` dicts in
`_retrieve_information`
- Add `setdefault('total', 0)` guard after successful KB retrieval to
handle cases where the retrieval result omits the key
- Accumulate `total` correctly in the merge branch of
`_async_update_chunk_info`
## Test plan
- [ ] Start a chat with Tavily configured and no knowledge base
- [ ] Verify no `KeyError: 'total'` is raised
- [ ] Verify Tavily results are returned correctly
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Fixes#14360
## Problem
When the same blob storage bucket is connected to multiple knowledge
bases (each through a different data source connector), the sync
pipeline hashes only the blob path
(`bucket_type:bucket_name:object_key`) to derive the document ID. Every
connector pointing at the same bucket therefore produces **identical
IDs** for the same object. The collision guard in
`FileService.upload_document` then fires for the second knowledge base:
```
Existing document id collision with another knowledge base; skipping update.
```
This makes it impossible to index the same bucket into more than one KB
simultaneously.
## Solution
Include `connector_id` in the hash input so that each connector produces
a distinct document ID even when the underlying blob path is identical:
```python
# Before
"id": hash128(doc.id),
# After
"id": hash128(f"{task['connector_id']}:{doc.id}"),
```
Because each KB connection uses its own connector (with a unique
`connector_id`), documents are now namespaced per connector and no
collision occurs.
**Note:** This is a breaking change for existing synced data sources.
After upgrading, a re-sync will create new documents with the updated ID
format. Old documents (indexed under the previous format) will remain in
the database but can be manually deleted or cleaned up via a re-sync
with reindex enabled.
## Testing
- Verified that the one-line change produces unique IDs for two
connectors pointing at the same S3 path.
- Existing unit test
`test_upload_document_skips_cross_kb_document_id_collision` continues to
pass — the collision guard in `FileService` is still valid for genuinely
colliding IDs from other sources.
---------
Co-authored-by: octo-patch <octo-patch@github.com>
### What problem does this PR solve?
Do not bypass threshold for rerank when metadata filter is enabled
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes#14651.
`kb_prompt()` in `rag/prompts/generator.py` crashes with
`AttributeError: 'NoneType' object has no attribute 'items'` during
agent citation generation when a retrieved chunk carries
`document_metadata: null`.
**Root cause.** The crash happens at `rag/prompts/generator.py:132-133`:
```python
meta = ck.get("document_metadata", {})
for k, v in meta.items():
```
`dict.get(key, default)` only returns the default when the key is
*missing*. When the key is present with an explicit `None` value,
`.get()` returns `None`, and `.items()` crashes.
**How the chunk gets `None`.** It's a round-trip inside RAGFlow itself,
not bad input from retrieval:
1. The agent stores retrieved chunks via `agent/canvas.py:814`, which
routes them through `chunks_format()`.
2. `rag/prompts/generator.py:61` canonicalizes the field with
`chunk.get("document_metadata")` (no default), so chunks without
metadata become `{"document_metadata": None, ...}`.
3. `agent/component/agent_with_tools.py:314` feeds those canonicalized
chunks back into `kb_prompt()` for citation generation, and
`.get("document_metadata", {})` no longer protects us.
**Fix.** One-line change at `rag/prompts/generator.py:132`: use
`ck.get("document_metadata") or {}` so an explicit `None` is also
coerced to `{}`.
The line-61 `None` is intentionally part of the API/UI contract — the
frontend handles it via optional chaining
(`web/src/components/markdown-content/index.tsx:184`,
`web/src/pages/next-search/search-view.tsx:217`) — so the fix belongs at
the consumer, not the producer.
### 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):
## Summary
Fixes file collision between different datasets when using Azure Blob
storage (SPN or SAS authentication).
## Bug
azure_spn_conn.py and zure_sas_conn.py ignored the ucket parameter
entirely, storing all files flat with just the filename. This caused
files with the same name from different datasets (knowledge bases) to
overwrite each other.
## Fix
Prepend bucket/ as a path prefix in all methods (put,
m, get, obj_exist, get_presigned_url, health) to match the behavior of
MinIO and S3 implementations.
## Changes
- **rag/utils/azure_spn_conn.py**: Added {bucket}/ prefix to file paths
in all operations
- **rag/utils/azure_sas_conn.py**: Same fix applied for consistency
(also noted in the original issue)
## Testing
Manual verification: files from different datasets now stored under
distinct bucket/ prefixes, preventing collisions.
Fixes#14159
Co-authored-by: Hunter <hunter@yitong.ai>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
Fixes#14159 — files from different datasets can overwrite each other in
Azure Blob storage.
## Problem
Both `azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket`
parameter in all storage operations (`put`, `get`, `rm`, `obj_exist`,
`get_presigned_url`). Files are stored flat using only the filename, so
two datasets containing a file with the same name will overwrite each
other.
The MinIO and S3 implementations correctly use the bucket (typically the
knowledge base ID) as a path prefix to create logical folder isolation:
- MinIO: uses `use_prefix_path` decorator → `{orig_bucket}/{fnm}`
- S3: uses `use_prefix_path` decorator → `{prefix_path}/{bucket}/{fnm}`
## Fix
Prepend `{bucket}/` to the file path in all 5 operations across both
Azure connector files:
| File | Methods fixed |
|------|---------------|
| `azure_spn_conn.py` | `put`, `get`, `rm`, `obj_exist`,
`get_presigned_url` |
| `azure_sas_conn.py` | `put`, `get`, `rm`, `obj_exist`,
`get_presigned_url` |
This matches the existing convention where `bucket` is the knowledge
base ID used as a directory prefix.
## ⚠️ Migration Note
Existing Azure SPN/SAS deployments have files stored without the bucket
prefix. After this fix, new files will be stored under
`{bucket}/{filename}` while existing files remain at `{filename}`. A
one-time migration script or manual file move may be needed for existing
deployments. New deployments are unaffected.
## Testing
- Verified the fix is consistent across all 5 methods in both files
- The `health()` method is intentionally left unchanged as it uses a
hardcoded test filename without bucket semantics
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Fixes#14551
### What problem does this PR solve?
The Moodle connector did not let the sync runner clean up indexed
documents that were deleted from the source. Other connectors such as
dropbox, seafile, webdav, and rss already do this through a slim
snapshot pass. This PR adds the same support for Moodle.
When `sync_deleted_files` is on, the runner now asks the Moodle
connector for a lightweight list of every module id that could be
indexed. The runner then compares this list with the index and removes
any indexed document whose id is not in the list.
The slim pass does not download files. It only goes through courses and
modules and yields ids. The id format matches the ids that the loader
produces, so the match is exact.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Notes
- `MoodleConnector` now also implements `SlimConnectorWithPermSync`.
- New `retrieve_all_slim_docs_perm_sync` yields slim docs with the same
ids the loader uses (`moodle_resource_<id>`, `moodle_forum_<id>`,
`moodle_page_<id>`, `moodle_book_<id>`, `moodle_assign_<id>`,
`moodle_quiz_<id>`).
- The `Moodle` sync class now returns `(document_generator, file_list)`
so the runner can do the cleanup. If the slim snapshot fails,
`file_list` is set back to `None` and the run continues without cleanup.
- The web data source map exposes `syncDeletedFiles` for Moodle so the
option shows up in the UI.
### How was this tested?
- `ruff check` passes on the changed Python files.
- Manual review of the produced slim ids against the ids the loader
builds in `_process_resource`, `_process_forum`, `_process_page`,
`_process_book`, and `_process_activity`.
- Behavior parity with the merged dropbox (#14476), seafile (#14499),
webdav (#14491), and rss (#14493) PRs.
Fixes#14159
## Problem
The `put()`, `get()`, `rm()`, and `obj_exist()` methods in both
`azure_spn_conn.py` and `azure_sas_conn.py` ignore the `bucket`
parameter entirely, storing all files flat using only the filename. This
causes files from different datasets to overwrite each other when they
share the same filename.
By contrast, the MinIO and S3 implementations correctly use the bucket
(typically the knowledge base ID) as a path prefix, creating logical
folder isolation like `{kb_id}/{filename}`.
## Solution
Prepend the `bucket` parameter as a path prefix to all file operations
in both Azure storage implementations:
- `azure_spn_conn.py`: `create_file`, `delete_file`, `get_file_client`
now use `f"{bucket}/{fnm}"`
- `azure_sas_conn.py`: `upload_blob`, `delete_blob`, `download_blob`,
`get_blob_client` now use `f"{bucket}/{fnm}"`
This matches the behavior of all other storage backends (MinIO, S3) and
prevents filename collisions across knowledge bases.
## Testing
- Verified the fix aligns with how MinIO/S3 connectors handle the bucket
parameter
- The `health()` method is left unchanged as it uses a fixed test path
for connectivity checks only
Co-authored-by: octo-patch <octo-patch@github.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Feat: enable sync deleted files for RDBMS & fix remove last file issue
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
## Summary
- Add MiniMax provider GroupId query parameter support in `LiteLLMBase`
- Extract `group_id` from key configuration in `__init__`
- Append `GroupId` as query parameter to `api_base` in
`_construct_complete_args`
## Why this change is needed
MiniMax provides an OpenAI-compatible API endpoint
(`/v1/chat/completions`), but `GroupId` is a MiniMax-specific account
identifier required for billing and rate limiting - it is not part of
the OpenAI standard.
Looking at LiteLLM's `MinimaxChatConfig`:
- `get_complete_url()` only constructs the base URL (e.g.,
`https://api.minimaxi.com/v1/chat/completions`)
- LiteLLM does **not** automatically inject `GroupId` into requests
- This must be handled by the caller (ragflow's chat_model.py)
The implementation appends `GroupId` as a query parameter to `api_base`:
```python
api_base = completion_args.get("api_base", self.base_url)
separator = "&" if "?" in api_base else "?"
completion_args["api_base"] = f"{api_base}{separator}GroupId={self.group_id}"
```
This matches MiniMax's official API format (as documented by
LlamaFactory):
```bash
curl --location 'https://api.minimaxi.chat/v1/text/chatcompletion?GroupId=你的GroupId' \
--header 'Authorization: Bearer 你的API_Key'
```
## Test plan
- [ ] Verify MiniMax API calls work with GroupId query parameter
- [ ] Verify backward compatibility for other providers
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This PR addresses three related GraphRAG reliability issues that
together allow long-running GraphRAG tasks (10+ hours of LLM extraction)
to be resumed after a crash or pause without re-doing completed work. It
builds on #14096 (per-doc subgraph cache) and extends the same idea to
the resolution and community-detection phases.
Fixes#14236.
## 1. Fix concurrent merge crash
Long GraphRAG runs would crash near the end of entity resolution with:
```
RuntimeError: dictionary keys changed during iteration
```
in `Extractor._merge_graph_nodes`. Two changes:
- `rag/graphrag/general/extractor.py`: snapshot `graph.neighbors(node1)`
via `list(...)` before iterating, so concurrent `add_edge` /
`remove_node` mutations on the shared `nx.Graph` cannot invalidate the
iterator. Also tracks each redirected neighbour in `node0_neighbors` so
a later merged node sharing the same external neighbour takes the
edge-merge branch instead of overwriting via `add_edge`.
- `rag/graphrag/entity_resolution.py`: serialize the merge step with a
dedicated `asyncio.Semaphore(1)`. `nx.Graph` is not thread-safe and
concurrent merges on overlapping neighbourhoods can produce incorrect
results even with the snapshot fix.
## 2. Don't wipe partial graph on pause
Previously the pause / cancel UI path called
`settings.docStoreConn.delete({"knowledge_graph_kwd": [...]}, ...)`,
destroying every subgraph, entity, relation, and graph row.
Re-triggering then started GraphRAG from scratch even though #14096 had
already added `load_subgraph_from_store`.
After main was merged in (which deleted `api/apps/kb_app.py` per
#14394), the pause path now lives on the new REST surface `DELETE
/v1/datasets/<id>/<index_type>`:
- `api/apps/services/dataset_api_service.py`: `delete_index` accepts a
`wipe: bool = True` parameter. When `False` the doc-store rows and
GraphRAG phase markers are left intact and only the running task is
cancelled. Default preserves historical behaviour.
- `api/apps/restful_apis/dataset_api.py`: parses `?wipe=false|0|no|off`
from the query string and forwards it.
- `web/src/utils/api.ts` + `web/src/services/knowledge-service.ts`:
`unbindPipelineTask` appends `?wipe=false` when explicitly false.
- The GraphRAG pause action in
`web/src/pages/dataset/dataset/generate-button/hook.ts` passes `wipe:
false` for `KnowledgeGraph`; raptor is unchanged.
**UX impact:** the pause icon next to a running GraphRAG task no longer
wipes graph data. The only path that still wipes is the explicit Delete
action in `GenerateLogButton` (trash icon behind a confirmation modal).
## 3. Phase-completion markers (`rag/graphrag/phase_markers.py`)
A small Redis-backed marker layer at
`graphrag:phase:{kb_id}:{resolution_done|community_done}` (7-day TTL).
`run_graphrag_for_kb` consults the markers on entry and skips phases
that already completed in a prior run. Markers are cleared automatically
when:
- new docs are merged into the graph (which invalidates prior resolution
and community results),
- `delete_index` wipes the graph, or
- `delete_knowledge_graph` is called.
Redis failures never block a run -- markers are an optimization, not a
gate.
## 4. Idempotent community detection
`extract_community` previously did `delete-then-insert` on
`community_report` rows; a crash mid-insert left the dataset with no
reports. Now report IDs are derived deterministically from `(kb_id,
community.title)`, the existing report IDs are snapshotted before
insert, new rows are written, then only stale rows are pruned. A failure
at any step leaves either the prior or the new report set intact --
never a partial mix.
## 5. Tunable doc-store insert pipeline
The GraphRAG insert loop in `rag/graphrag/utils.py` and the
`community_report` insert in `rag/graphrag/general/index.py` were both
hardcoded to `es_bulk_size = 4` and ran strictly sequentially. On a real
KB this meant 1077 chunks took ~21 minutes for a 100-chunk slice -- pure
round-trip overhead.
- New `insert_chunks_bounded()` helper in `rag/graphrag/utils.py`
batches inserts via a bounded `asyncio.Semaphore`. Same retry / timeout
semantics as the prior loop.
- Defaults: 64 docs per batch, 4 batches in flight (matches the regular
ingest pipeline in `document_service.py`). Tunable per-deployment via
`GRAPHRAG_INSERT_BULK_SIZE` and `GRAPHRAG_INSERT_CONCURRENCY`.
- Both `set_graph` and `extract_community` now use the helper.
This dropped the same 1077-chunk insert from minutes to seconds in local
testing without measurable extra pressure on Infinity (total in-flight
docs ≤ `BULK_SIZE × CONCURRENCY` = 256 by default).
## Tests
- `test/unit_test/rag/graphrag/test_merge_graph_nodes.py` (3 tests):
dense neighbourhood merge, neighbour-snapshot regression, concurrent
serialized merges.
- `test/unit_test/rag/graphrag/test_phase_markers.py` (4 tests): set/has
round-trip, kb-scoped clear, no-op on empty input, graceful Redis
failure.
-
`test/testcases/test_web_api/test_dataset_management/test_dataset_sdk_routes_unit.py`:
new `test_delete_index_wipe_flag_unit` covers `wipe=false` for both
GraphRAG and raptor on the new REST route, and confirms the default
still wipes and clears phase markers.
## Compatibility
- Backward compatible: tasks queued before this change behave
identically (default `wipe=true`, no markers expected).
- No schema/migration changes; all new state lives in Redis.
- New optional REST query param `wipe` on `DELETE
/v1/datasets/<id>/<index_type>`.
- New optional env vars `GRAPHRAG_INSERT_BULK_SIZE` and
`GRAPHRAG_INSERT_CONCURRENCY`; defaults preserve safe behaviour.
## Example of resume
Screenshot below shows a test resuming knowledge graph generation after
applying the concurrency fix and re-deploying.
<img width="521" height="677" alt="image"
src="https://github.com/user-attachments/assets/9ef0d405-cbb3-420d-a1a1-e51f3e7e9b7a"
/>
### 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?
This PR fixes a bug where `layout_recognize="<name>@OpenDataLoader"` was
misrouted and then failed during parsing in the naive parser path. It
now routes correctly to OpenDataLoader and avoids passing unsupported
arguments that caused runtime errors. fixes#14572
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix#14340
## Problem Description
When using an **Agentic Agent** (not Workflow) with one or more
Retrieval tools (e.g., Dataset Retrieval + Memory Retrieval), the agent
silently returns an empty response (`agent_response: ""`) after hanging
for several minutes. The server logs show:
```
AttributeError: 'ChatCompletionMessageToolCall' object has no attribute 'index'
```
This error propagates as a `GENERIC_ERROR`, causing the canvas to return
an empty response. The subsequent Memory save task then receives the
empty `agent_response` and logs:
```
Document for referred_document_id XXXX not found
```
## Reproduction Steps
1. Set `DOC_ENGINE=infinity` (or `elasticsearch` — the engine itself is
not the root cause).
2. Create a blank **Agentic Agent** (not a Workflow).
3. Add **two Retrieval tools** to the Agent node:
- `Retrieval_DS` → Dataset (Knowledge Base)
- `Retrieval_Mem` → Memory component
4. Add a **Message** node with **Save to Memory** enabled.
5. Launch the agent and send any message (e.g., "hola").
6. The agent hangs and returns an empty response.
## Root Cause Analysis
The crash occurs in `_append_history` and `_append_history_batch` inside
`rag/llm/chat_model.py`. These methods directly access `.index` on tool
call objects:
```python
# _append_history_batch
{
"index": tc.index, # <-- crashes here
...
}
```
However, **non-streaming** LLM responses (`stream=False`) return
`ChatCompletionMessageToolCall` objects, which **do not have an `index`
field** according to the OpenAI API specification. The `index` field
only exists on `ChoiceDeltaToolCall` objects returned in **streaming**
responses (`stream=True`).
When the agentic agent triggers an internal `full_question` call (used
to compress multi-turn conversation history), the request is incorrectly
routed through `async_chat_with_tools` because `is_tools=True` is set at
the `LLMBundle` level. If the LLM decides to emit `tool_calls` during
this auxiliary request, the code enters the non-streaming tool loop and
crashes when trying to append history.
## Fix
Replaced all direct `.index` accesses with `getattr(..., "index", None)`
for safe, backward-compatible access:
| Method | File | Line | Change |
|--------|------|------|--------|
| `_append_history` | `rag/llm/chat_model.py` | ~L304 |
`tool_call.index` → `getattr(tool_call, "index", None)` |
| `_append_history_batch` | `rag/llm/chat_model.py` | ~L332 | `tc.index`
→ `getattr(tc, "index", None)` |
| `_append_history` | `rag/llm/chat_model.py` | ~L1467 |
`tool_call.index` → `getattr(tool_call, "index", None)` |
| `_append_history_batch` | `rag/llm/chat_model.py` | ~L1496 |
`tc.index` → `getattr(tc, "index", None)` |
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: noob <yixiao121314@outlook.com>
### What problem does this PR solve?
add IMAP deleted document sync
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Incremental DingTalk AI Table (Notable) sync did not reconcile rows
removed on the remote side with documents already in the knowledge base.
This follows the coordinated datasource work in #14362 (“sync deleted
files”).
This PR adds a **full slim snapshot**
(`retrieve_all_slim_docs_perm_sync`) that lists **current record IDs for
all sheets** without building document blobs, using the same logical
document IDs as full ingest
(`dingtalk_ai_table:{table_id}:{sheet_id}:{record_id}`). When
**`sync_deleted_files`** is enabled on incremental runs,
`DingTalkAITable._generate` returns **`(document_generator,
file_list)`** so **`SyncBase`** can run
**`cleanup_stale_documents_for_task`** and remove KB rows that no longer
exist remotely.
Design notes:
- **`_document_id`** centralizes the ID string so slim snapshots and
**`_convert_record_to_document`** stay aligned with
**`hash128(doc.id)`** semantics used during ingestion/cleanup.
- **`end_ts`** is captured before building **`file_list`**, then
**`poll_source`** uses the same upper bound (consistent with other
Dropbox-style connectors).
- **`batch_size`** from connector config is coerced to a positive
**`int`** before constructing the connector.
- Slim snapshot failures are caught in **`_generate`**; **`file_list`**
is set to **`None`** so cleanup is skipped rather than running on
partial/error state.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Files changed (summary)
| Area | Change |
|------|--------|
| `common/data_source/dingtalk_ai_table_connector.py` |
`SlimConnectorWithPermSync`, `retrieve_all_slim_docs_perm_sync`,
`_document_id` shared with document conversion |
| `rag/svr/sync_data_source.py` | `DingTalkAITable._generate`: slim
snapshot + tuple return; `batch_size` validation; shared `end_ts` with
`poll_source` |
| `web/src/pages/user-setting/data-source/constant/index.tsx` |
`syncDeletedFiles` for DingTalk AI Table in
`DataSourceFeatureVisibilityMap` |
Closes / relates to: #14362
### What problem does this PR solve?
Currently, RAGFlow's Search and Chat interfaces display only raw
vectorized text chunks during retrieval, without contextual information
about their source documents. Users cannot see document titles, page
numbers, upload dates, or custom metadata fields that would help them
understand and trust the retrieved results.
This PR introduces an **optional metadata display feature** that
enriches retrieved chunks with document-level metadata in both the
Search tab and Chatbot interface.
**Key improvements:**
- **Search results**: Display document metadata as styled badges beneath
chunk snippets
- **Chat citations**: Show metadata in citation popovers and reference
lists for better source context
- **LLM context**: Metadata is injected into the LLM prompt to enable
more accurate, citation-aware responses
- **External API support**: Applications using RAGFlow's SDK retrieval
endpoints (`/v1/retrieval`, `/v1/searchbots/retrieval_test`) can opt-in
via request parameters
- **User control**: Multi-select dropdown UI allows users to choose
which metadata fields to display
**Implementation approach:**
- ✅ Reuses existing `DocMetadataService` infrastructure (no new database
tables or indices)
- ✅ Settings stored in existing JSON configuration fields
(`search_config.reference_metadata`, `prompt_config.reference_metadata`)
- ✅ No database migrations required
- ✅ Disabled by default (fully opt-in and backward-compatible)
- ✅ Dynamic metadata field selection populated from actual document
metadata keys
- ✅ Fixed critical bug where Python's builtin `set()` was shadowed by a
route handler function
**Modified endpoints (all backward-compatible):**
- `POST /v1/retrieval` (Public SDK)
- `POST /v1/searchbots/retrieval_test` (Searchbots)
- `POST /v1/chunk/retrieval_test` (UI/Internal)
- Chat completions endpoints (via `extra_body.reference_metadata` or
`prompt_config`)
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
###Images
-
<img width="879" height="1275" alt="image"
src="https://github.com/user-attachments/assets/95b2d731-31ae-45a1-b081-bf5893f52aeb"
/>
<br><br>
<br><br>
<img width="1532" height="362" alt="image"
src="https://github.com/user-attachments/assets/9cebc65b-b7a7-459f-b25e-3b13fa9b638e"
/>
<br><br>
<br><br>
<img width="2586" height="1320" alt="image"
src="https://github.com/user-attachments/assets/2153d493-d899-461f-a7a9-041391e07776"
/>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Attili-sys <Attili-sys@users.noreply.github.com>
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
### What problem does this PR solve?
Partially addresses #14362.
This PR enables syncing deleted files for RSS data sources.
Previously, RSS incremental sync only returned feed entries whose
timestamps were inside the poll window. If an entry was removed from the
RSS feed, RAGFlow had no full current RSS snapshot to pass into the
shared stale-document cleanup path, so the deleted remote entry could
remain in the knowledge base.
This PR:
- adds `retrieve_all_slim_docs_perm_sync()` to `RSSConnector`
- reuses the same `rss:<md5(stable_key)>` document ID derivation used by
normal RSS ingest
- returns `(document_generator, file_list)` for incremental RSS sync
when `sync_deleted_files` is enabled
- captures the poll end timestamp before snapshot/poll so cleanup does
not race against the same sync window
- adds start/end logs around RSS slim snapshot collection
- exposes the deleted-file sync toggle for RSS in the data source UI
Per maintainer request on related datasource PRs, this PR contains no
test-case changes. Local verification was run with an external script.
Validation:
- `uv run ruff check common/data_source/rss_connector.py
rag/svr/sync_data_source.py`
- `uv run pytest test/unit_test/rag/test_sync_data_source.py -q`
- `./node_modules/.bin/eslint
src/pages/user-setting/data-source/constant/index.tsx`
- `git diff --check`
- `uv run python /tmp/verify_rss_deleted_sync.py --repo
/root/74/ragflow`
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## What problem does this PR solve?
Incremental WebDAV sync only ingested files whose modification time fell
inside the poll window; documents removed on the WebDAV server were
never removed from the knowledge base. This aligns with
[#14362](https://github.com/infiniflow/ragflow/issues/14362)
(coordinated datasource “sync deleted files” work).
This PR adds a **full-tree slim snapshot**
(`retrieve_all_slim_docs_perm_sync`) that enumerates current remote
paths **without downloading file contents**, using the same logical
document IDs as full ingest (`webdav:{base_url}:{file_path}`). When
**`sync_deleted_files`** is enabled on incremental runs, sync returns
**`(document_generator, file_list)`** so **`SyncBase`** runs
**`cleanup_stale_documents_for_task`** and removes KB rows no longer
present remotely.
Design notes:
- **`_list_files_recursive`** gains **`filter_by_mtime`**: snapshot
passes **`filter_by_mtime=False`** (full tree under **`remote_path`**);
**`poll_source`** keeps mtime-window filtering as before.
- Slim snapshot applies the same **extension** and **`size_threshold`**
rules as **`_yield_webdav_documents`** so retain IDs match what would be
indexed.
- **`end_ts`** is captured before building **`file_list`**, then
**`poll_source`** uses the same upper bound (consistent with
Dropbox-style connectors).
## Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Files changed
| Area | Change |
|------|--------|
| `common/data_source/webdav_connector.py` |
`SlimConnectorWithPermSync`, `retrieve_all_slim_docs_perm_sync`,
`filter_by_mtime` on `_list_files_recursive` |
| `rag/svr/sync_data_source.py` | WebDAV `_generate`: `file_list` +
tuple return; pass **`batch_size`** from connector config |
| `web/src/pages/user-setting/data-source/constant/index.tsx` |
`syncDeletedFiles` for WebDAV in `DataSourceFeatureVisibilityMap` |
### What problem does this PR solve?
id as "text", not a "keyword", order by it will cause error.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Refs #14362.
This PR enables syncing deleted files for Zendesk data sources.
Previously, Zendesk incremental sync never returned a slim remote
snapshot to the shared stale-document cleanup path, so deleted remote
Zendesk records could remain in RAGFlow. The existing Zendesk slim
snapshot also included records that ingestion intentionally skips, such
as draft articles, articles without bodies, skipped-label articles,
empty-body articles, and tickets with `status == "deleted"`.
This PR:
- exposes the deleted-file sync option for Zendesk in the data source UI
- returns Zendesk slim snapshots during incremental sync when
`sync_deleted_files` is enabled
- reuses Zendesk indexability rules so cleanup compares against the same
records ingestion can materialize
- adds start/end logs around Zendesk slim snapshot collection for
operational visibility
Per maintainer request, this PR contains no test-case changes. Manual
verification recording will be provided separately.
Validation:
- `uv run ruff check common/data_source/zendesk_connector.py
rag/svr/sync_data_source.py`
- `uv run pytest test/unit_test/rag/test_sync_data_source.py -q`
- `./node_modules/.bin/eslint
src/pages/user-setting/data-source/constant/index.tsx`
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Partially addresses #14362.
Adds deleted-file sync support for the Asana data source. Asana already
indexes task attachments as documents, but it did not provide the slim
document snapshot required by stale-document reconciliation, and the
sync wrapper never returned a `file_list` for cleanup.
This PR:
- adds `retrieve_all_slim_docs_perm_sync()` to `AsanaConnector`
- builds slim IDs with the same `asana:{task_id}:{attachment_gid}`
format used by indexed documents
- avoids downloading attachment blobs during the snapshot
- aborts the snapshot if Asana API errors occur, preventing partial
snapshots from deleting valid local docs
- captures the incremental poll end time before snapshotting and makes
`poll_source()` respect that boundary
- exposes the deleted-file sync toggle for Asana in the data source UI
Per maintainer request, this PR contains no test-case changes. Manual
verification recording will be provided separately.
Validation:
- `uv run ruff check common/data_source/asana_connector.py
rag/svr/sync_data_source.py`
- `uv run pytest test/unit_test/rag/test_sync_data_source.py -q`
- `./node_modules/.bin/eslint
src/pages/user-setting/data-source/constant/index.tsx`
- `git diff --check`
### Type of change
- [x] New Feature
## Summary
Fix critical severity security issue in `rag/utils/ob_conn.py`.
## Vulnerability
| Field | Value |
|-------|-------|
| **ID** | V-003 |
| **Severity** | CRITICAL |
| **Scanner** | multi_agent_ai |
| **Rule** | `V-003` |
| **File** | `rag/utils/ob_conn.py:691` |
**Description**: The OceanBase database connector constructs SQL WHERE
clauses by directly embedding user-controlled filter expressions using
Python f-strings at lines 726, 777, 781, 787, 793, 821, and 827. No
parameterization or allowlist validation is applied before the
expressions are incorporated into live SQL queries. This is the most
critical vulnerability in the codebase because it directly exposes the
RAG knowledge base — the platform's core business asset — to complete
compromise.
## Changes
- `rag/utils/ob_conn.py`
## Verification
- [x] Build passes
- [x] Scanner re-scan confirms fix
- [x] LLM code review passed
---
*Automated security fix by [OrbisAI Security](https://orbisappsec.com)*
### What problem does this PR solve?
Feat: add button for remove header & footer in pipeline
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Incremental Seafile sync only ingests files whose modification time
falls in the poll window; documents removed in Seafile were never
removed from the knowledge base. This contributes to
[#14362](https://github.com/infiniflow/ragflow/issues/14362) (datasource
“sync deleted files” coordination).
This PR adds a **slim snapshot** (`retrieve_all_slim_docs_perm_sync`)
that enumerates current remote file IDs **without downloading content**,
using the same logical IDs as full ingest
(`seafile:{repo_id}:{file_id}`). When **`sync_deleted_files`** is
enabled on incremental runs, **`SeaFile._generate`** returns
**`(document_generator, file_list)`** so **`SyncBase`** can run
**`cleanup_stale_documents_for_task`** and remove stale KB documents.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What changed
- **`common/data_source/seafile_connector.py`**: `SeaFileConnector`
implements **`SlimConnectorWithPermSync`**;
**`_list_files_recursive(..., filter_by_mtime=...)`** supports full-tree
listing for snapshots; **`retrieve_all_slim_docs_perm_sync()`** reuses
the same library/root scan as ingest and applies the same **size**
ceiling; logging for snapshot start/end and counts.
- **`rag/svr/sync_data_source.py`**: **`SeaFile._generate`** validates
**`batch_size`**, captures **`end_ts`** before snapshot +
**`poll_source`**, wraps slim retrieval in **`try`/`except`** (
**`file_list = None`** on failure so ingest continues), returns
**`(generator, file_list)`**.
- **`web/src/pages/user-setting/data-source/constant/index.tsx`**:
**`syncDeletedFiles`** for Seafile in
**`DataSourceFeatureVisibilityMap`**.
### What problem does this PR solve?
This fixes a crash in Manual and Naive parsing when PDF outlines include
page numbers as a third tuple value. It makes outline unpacking accept
extra values so parsing no longer fails. fixes#14411
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Both tokenizer (`rag/flow/tokenizer/tokenizer.py`) and
`BuiltinEmbed.encode`
(`rag/llm/embedding_model.py`) currently accumulate embedding batches
via
`np.concatenate` inside the per-batch loop. `np.concatenate` allocates a
new
array and copies all existing data on every call, so accumulating N
batches
is O(N²) in both time and peak memory.
Replacing the incremental concatenate with a list-of-batches + a single
`np.vstack` at the end gives O(N) total work.
For tokenizer the title-vector broadcast `np.concatenate([vts[0]] * N)`
is
also replaced by `np.tile`, which does the same job with a single
contiguous
allocation instead of building a Python list of references.
This is purely a CPU/memory optimisation — output shape and dtype are
unchanged. Measured impact grows with document size:
- 1k chunks (batch 512, 2 iters): ~negligible
- 10k chunks (20 iters): ~10× speedup on this stage
- 100k chunks (195 iters): ~100× speedup, and peak RAM
drops from O(N) extra to near-zero
### Type of change
- [x] Performance Improvement
Co-authored-by: yoan sapienza <Yoan Sapienza yoan.sapienza@orange.fr Yoan Sapienza zappy@macbookpro.home>
