Commit Graph

17 Commits

Author SHA1 Message Date
Jack
f6ff862a24 fix: restore case-insensitive contains/not contains/not in and consolidate metadata filter pipeline (#15686)
## Summary

This PR fixes case-sensitivity regressions introduced in #15656 and
consolidates the metadata filtering pipeline by removing the duplicate
`applySingleCondition` adapter layer.

### Bug fixes
1. **contains / not contains**: restored case-insensitive matching (was
lost when `applySingleCondition` was replaced by
`common.MetaFilter.matchValue` which lacked `strings.ToLower`)
2. **not in**: restored case-insensitive matching (was lost for same
reason; uses `strings.EqualFold`)
3. **!= with date filter values**: non-date metadata values now
correctly match the `≠` operator (a non-date value IS not equal to any
date, but was returning false)

### Architecture
4. **Removed `applySingleCondition`** (65 lines) — the inline switch was
a duplicate of `common.MetaFilter` logic. `ApplyMetaFilter` now converts
conditions and delegates to `common.MetaFilter` once per filter set,
eliminating ~25 lines of duplicate AND/OR merge logic.
5. **Added `filterSet`** — O(n+m) hash-map fast path for `in`/`not in`
operators, replacing the O(n*m) linear scan in `matchValue`.
6. **Exported `NormalizeOperator`** from `common` for consistent
operator alias handling.

### Cleanup
7. Removed 18 lines of dead code (`matchValue`'s `in`/`not in` branches
already bypassed by `filterOut` delegation)
8. Fixed orphaned godoc comment for `convertOperator`
9. Fixed incorrect `filterSet` doc comment (claimed "matching EqualFold"
but used `strings.ToLower`)
10. Completed `convertToMetaCondition` operator normalization
documentation

### Testing
- 60 tests (24 service + 36 common), all passing
- New tests: `==`, `≠`, `>`, `<`, `≥`, `≤`, `empty`, `not empty` through
`ApplyMetaFilter`
- New tests: `<`, `≤`, `≠` through `MetaFilter`; `not-in-empty-list`
through `filterSet`
- All 18 `MetaFilter` tests pass; all 10 `filterSet` unit tests pass

---------

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-05 12:47:55 +08:00
Jack
a237a89b90 feat: add QueryRewrite prompt builder and response parser (#15669)
QueryRewrite prompt builder and response parser. Zero external
dependencies.

### Functions
- `BuildQueryRewritePrompt`: Renders `minirag_query2kwd` prompt with
query and type pool
- `ParseQueryRewriteResponse`: Parses LLM JSON response with fallback
for markdown and extra text

### Testing
```
=== RUN   TestBuildQueryRewritePrompt             --- PASS
=== RUN   TestParseQueryRewriteResponse_ValidJSON --- PASS
=== RUN   TestParseQueryRewriteResponse_MarkdownBlock --- PASS
=== RUN   TestParseQueryRewriteResponse_ExtraText --- PASS
=== RUN   TestParseQueryRewriteResponse_Invalid   --- PASS
=== RUN   TestParseQueryRewriteResponse_EmptyEntities --- PASS
```

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-05 10:11:14 +08:00
Jack
bf6c091c9f feat: add KG scoring utilities (#15666)
KG scoring utilities as pure functions.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-05 10:10:59 +08:00
Jack
eee6ad546f feat: add ResolveReferenceMetadata utility function (#15663)
Add `ResolveReferenceMetadata` to parse `include_metadata` /
`metadata_fields` from request and config payloads.

### Changes
- **New**: `internal/common/reference_metadata.go` — pure function, zero
dependencies
- **New**: `internal/common/reference_metadata_test.go` — 8 test cases

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-04 22:34:18 +08:00
Jack
461c190c49 feat: migrate meta_filter and convert_conditions to Go (#15648)
## Summary

Migrate the metadata filtering utilities `meta_filter` and
`convert_conditions` from `common/metadata_utils.py` to Go as pure
functions with zero external dependencies.

These functions are used by `dify/retrieval`, `openai/chat/completions`,
`document_api`, and `chunk_api` for filtering documents by metadata
conditions.

### Changes

- **New**: `internal/common/metadata_utils.go` — `ConvertConditions()`
and `MetaFilter()` with full operator support
- **New**: `internal/common/metadata_utils_test.go` — 18 test cases
covering all operators and edge cases

### Supported Operators

`=`, `≠`, `>`, `<`, `≥`, `≤`, `contains`, `not contains`, `in`, `not
in`, `start with`, `end with`, `empty`, `not empty`

### Design

- Numeric comparison via `strconv.ParseFloat`
- Date comparison via YYYY-MM-DD format detection
- Case-insensitive string comparison fallback
- `and` / `or` logic support for multiple conditions
- Zero external dependencies — pure functions only
2026-06-04 20:14:27 +08:00
Haruko386
d766e49128 feat[Go]: implement /system/stats and refactor /system/config/log (#15407)
### What problem does this PR solve?

As title

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
2026-05-29 19:32:21 +08:00
Jin Hai
f8c626bbc8 Go: add ingestion server (#15094)
### What problem does this PR solve?

1. Go ingestion server will connected with admin server with gRPC stream
2. Go ingestion server will be responsible for ingestion tasks
```

RAGFlow(admin)> list ingestors;
+-----------------+-----------+----------------------------------+---------------------------+----------+------------+--------------+--------+------------+---------------+
| address         | cpu_usage | id                               | last_heartbeat            | name     | process_id | rss_usage    | status | task_count | vms_usage     |
+-----------------+-----------+----------------------------------+---------------------------+----------+------------+--------------+--------+------------+---------------+
| 127.0.0.1:58564 | 0         | bdd1870eea2646e0aacb8a2cd3307aa2 | 2026-05-24T18:16:17+08:00 | ingestor | 680152     | 212.72265625 | active | 0          | 2589.12109375 |
+-----------------+-----------+----------------------------------+---------------------------+----------+------------+--------------+--------+------------+---------------+

RAGFlow(admin)> start ingestion 'abc';
+----------------------------------+
| task_id                          |
+----------------------------------+
| e714777639ca4760ab427b5f211e81ad |
+----------------------------------+

RAGFlow(admin)> stop ingestion 'f7bd39d0a724457eb5fdce6d81699776';
+----------------------------------+
| task_id                          |
+----------------------------------+
| f7bd39d0a724457eb5fdce6d81699776 |
+----------------------------------+

RAGFlow(admin)> list tasks;
+-----+----------------------------------+-------+------+----------------------------------+---------------------------+------------+------------+
| ETA | assign_to                        | error | from | id                               | last_update               | start_time | status     |
+-----+----------------------------------+-------+------+----------------------------------+---------------------------+------------+------------+
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | eae6431da72a40e796cff3a03008091b | 2026-05-24T19:46:03+08:00 |            | COMPLETED  |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | 6cccdd174bd049ecb05a774bbb47593f | 2026-05-24T19:46:03+08:00 |            | COMPLETED  |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | ef360d777e57485799adb96b30f2b4b8 | 2026-05-24T19:46:03+08:00 |            | CANCELED   |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | bcc5c5448cb64de48b6b6171c36fb790 | 2026-05-24T19:46:03+08:00 |            | CANCELED   |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | bfc25384c43a443294fe2da979a38ac2 | 2026-05-24T19:46:03+08:00 |            | DISPATCHED |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | 84960537b85d413b8990a9efd5952d67 | 2026-05-24T19:46:04+08:00 |            | DISPATCHED |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | 3d223c1b51e24b36861a3bfb2f1d58d4 | 2026-05-24T19:46:03+08:00 |            | CANCELED   |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | e433b0e356b846c89c301621a3c54494 | 2026-05-24T19:46:03+08:00 |            | COMPLETED  |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | 7c93a3880f074ebd8eca14e6b51bb7ef | 2026-05-24T19:46:03+08:00 |            | COMPLETED  |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | df2e4ef51aaf4390bff9a23f2692486e | 2026-05-24T19:46:04+08:00 |            | DISPATCHED |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | 7377c53010194ef7a83aa206698d66ff | 2026-05-24T19:46:05+08:00 |            | DISPATCHED |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | df64d1a1f9d348e3a2f174c4d7d69e73 | 2026-05-24T19:46:05+08:00 |            | DISPATCHED |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | b59834512e2847e1bdf13ace04b8a456 | 2026-05-24T19:46:06+08:00 |            | DISPATCHED |
| 0   | 17937da188b84f23a5c10bb87588944b |       | CLI  | 0064bb0ab69344028d1ecfda053826f4 | 2026-05-24T19:46:03+08:00 |            | QUEUED     |
+-----+----------------------------------+-------+------+----------------------------------+---------------------------+------------+------------+


```


### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-05-25 14:00:08 +08:00
Jin Hai
17d71e5d79 Go CLI: embed and rerank (#14735)
### What problem does this PR solve?

```
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'embedding-3@test@zhipu-ai' dimension 16;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 16        | 0     |
| 16        | 1     |
+-----------+-------+

RAGFlow(user)> rerank query 'what is rag' document 'rag is retrieval augment generation' 'rag need llm' 'famous rag project includes ragflow' with 'rerank@test@zhipu-ai' top 2;
+-------+-----------------+
| index | relevance_score |
+-------+-----------------+
| 0     | 1               |
| 2     | 0.99999976      |
+-------+-----------------+
```

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-05-09 17:41:54 +08:00
Jin Hai
aa57b5bd8b Go: move logger to common module (#14545)
### What problem does this PR solve?

As title

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-05-06 10:41:58 +08:00
qinling0210
1473000135 Implement retrieval_test in GO (#14231)
### What problem does this PR solve?

Implement retrieval_test in GO

### Type of change

- [x] Refactoring
2026-04-24 15:30:14 +08:00
Jin Hai
5951e2b564 Go: Add create search (#13998)
### What problem does this PR solve?

As title

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-09 20:04:06 +08:00
chanx
21af67f6f9 feat(File Management): Refactor File List API and Add Knowledge Base Document Initialization (#13914)
### What problem does this PR solve?

feat(File Management): Refactor File List API and Add Knowledge Base
Document Initialization

- Migrate the file list API endpoint from `/v1/file/list` to
`/api/v1/files` to align with the Python implementation.
- Add logic for initializing knowledge base documents; automatically
create the `.knowledgebase` folder and associated documents when
retrieving the root directory.
- Enhance parameter validation and error handling, including the
introduction of a new `CodeParamError` error code.
- Optimize the file list response structure to match the implementation
on the Python side.
- Update the Vite configuration to support proxying the new
`/api/v1/files` endpoint.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2026-04-03 15:08:43 +08:00
Magicbook1108
cfe6ea6f56 Feat: CREATE / DELETE / LIST dataset api in Go (#13695)
### What problem does this PR solve?

Feat: CREATE / DELETE / LIST dataset api in Go

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
2026-03-19 20:48:32 +08:00
Jin Hai
5c955a31cc Update go server (#13589)
### What problem does this PR solve?

1. Add more CLI command
2. Add some license hooks

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-03-13 14:41:02 +08:00
Jin Hai
7f6a9e8ee9 Update ext field type of heartbeat message (#13490)
### What problem does this PR solve?

As title

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-03-10 10:49:39 +08:00
Jin Hai
52bcd98d29 Add scheduled tasks (#13470)
### What problem does this PR solve?

1. RAGFlow server will send heartbeat periodically.
2. This PR will including:
- Scheduled task
- API server message sending
- Admin server API to receive the message.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-03-09 17:48:29 +08:00
chanx
81fd1811b8 Feat:Using Go to implement user registration logic (#13431)
### What problem does this PR solve?

Feat:Using Go to implement user registration logic

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2026-03-06 16:42:49 +08:00