Files
ragflow/test/testcases/test_sdk_api/conftest.py
euvre 4dcc42e0e1 feat(api): add unified index API and dataset management endpoints (#14222)
### What problem does this PR solve?

## Summary

Refactor the dataset API layer into a clean service/REST separation
pattern, add a unified `/index` API for graph/raptor/mindmap operations,
and introduce several new dataset management endpoints with full test
coverage.

## Changes

### Service Layer (`dataset_api_service.py`)

- Added `trace_index(dataset_id, tenant_id, index_type)` — unified trace
function for all index types
- Added `run_index`, `delete_index` service functions
- Added `get_dataset`, `get_ingestion_summary`, `list_ingestion_logs`,
`get_ingestion_log`
- Added `run_embedding`, `list_tags`, `aggregate_tags`, `delete_tags`,
`rename_tag`
- Added `get_flattened_metadata`, `get_auto_metadata`,
`update_auto_metadata`

### REST API Layer (`dataset_api.py`)

**New unified routes:**

| Method | Route | Description |
|--------|-------|-------------|
| POST | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Run index
task |
| GET | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Trace index
task |
| DELETE | `/datasets/<id>/<index_type>` | Delete index |
| GET | `/datasets/<id>` | Get dataset details |
| GET | `/datasets/<id>/ingestions/summary` | Ingestion summary |
| GET | `/datasets/<id>/ingestions` | List ingestion logs |
| GET | `/datasets/<id>/ingestions/<log_id>` | Get single ingestion log
|
| POST | `/datasets/<id>/embedding` | Run embedding |
| GET | `/datasets/<id>/tags` | List tags |
| GET | `/datasets/tags/aggregation` | Aggregate tags across datasets |
| DELETE | `/datasets/<id>/tags` | Delete tags |
| PUT | `/datasets/<id>/tags` | Rename tag |
| GET | `/datasets/metadata/flattened` | Get flattened metadata |
| GET/PUT | `/datasets/<id>/metadata/config` | New metadata config path
|

**Removed routes (replaced by unified `/index`):**

- `POST /datasets/<id>/mindmap`
- `GET /datasets/<id>/mindmap`

**Preserved legacy routes (backward compatibility):**

- `/run_graphrag`, `/trace_graphrag`, `/run_raptor`, `/trace_raptor`
- `/auto_metadata` GET/PUT

### Test Suite

- Updated `common.py` helpers: added `trace_index`, removed
`run_mindmap`/`trace_mindmap`
- Added 7 new test files with 39 test cases total:

| Test File | Cases |
|-----------|-------|
| `test_get_dataset.py` | 4 |
| `test_ingestion_summary.py` | 2 |
| `test_ingestion_logs.py` | 5 |
| `test_index_api.py` | 14 |
| `test_embedding.py` | 2 |
| `test_tags.py` | 8 |
| `test_flattened_metadata.py` | 4 |

- Deleted `test_mindmap_tasks.py` (covered by unified index tests)

## Design Decisions

1. **Unified `/index?type=...`** — single endpoint replaces 3 separate
route pairs for graph/raptor/mindmap
2. **Backward compatibility** — old routes (`/run_graphrag`,
`/run_raptor`, `/auto_metadata`) preserved alongside new paths
3. **`_VALID_INDEX_TYPES = {"graph", "raptor", "mindmap"}`** — input
validation via constant set
4. **`_INDEX_TYPE_TO_TASK_ID_FIELD`** — maps index type to KB model task
ID field for clean dispatch

## Files Changed

- `api/apps/restful_apis/dataset_api.py`
- `api/apps/services/dataset_api_service.py`
- `sdk/python/ragflow_sdk/modules/dataset.py`
- `test/testcases/test_http_api/common.py`
- `test/testcases/test_http_api/test_dataset_management/` (7 new files)
### Type of change

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

---------

Signed-off-by: noob <yixiao121314@outlook.com>
2026-04-27 09:38:01 +08:00

178 lines
5.2 KiB
Python

#
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from pathlib import Path
from time import sleep
import pytest
from common import (
batch_add_chunks,
batch_create_chat_assistants,
batch_create_datasets,
bulk_upload_documents,
delete_all_chats,
delete_all_chunks,
delete_all_datasets,
delete_all_sessions,
)
from configs import HOST_ADDRESS, VERSION
from pytest import FixtureRequest
from ragflow_sdk import Chat, Chunk, DataSet, Document, RAGFlow
from utils import wait_for
from utils.file_utils import (
create_docx_file,
create_eml_file,
create_excel_file,
create_html_file,
create_image_file,
create_json_file,
create_md_file,
create_pdf_file,
create_ppt_file,
create_txt_file,
)
@wait_for(200, 1, "Document parsing timeout")
def condition(_dataset: DataSet):
documents = _dataset.list_documents(page_size=1000)
for document in documents:
if document.run != "DONE":
return False
return True
@pytest.fixture
def generate_test_files(request: FixtureRequest, tmp_path: Path):
file_creators = {
"docx": (tmp_path / "ragflow_test.docx", create_docx_file),
"excel": (tmp_path / "ragflow_test.xlsx", create_excel_file),
"ppt": (tmp_path / "ragflow_test.pptx", create_ppt_file),
"image": (tmp_path / "ragflow_test.png", create_image_file),
"pdf": (tmp_path / "ragflow_test.pdf", create_pdf_file),
"txt": (tmp_path / "ragflow_test.txt", create_txt_file),
"md": (tmp_path / "ragflow_test.md", create_md_file),
"json": (tmp_path / "ragflow_test.json", create_json_file),
"eml": (tmp_path / "ragflow_test.eml", create_eml_file),
"html": (tmp_path / "ragflow_test.html", create_html_file),
}
files = {}
for file_type, (file_path, creator_func) in file_creators.items():
if request.param in ["", file_type]:
creator_func(file_path)
files[file_type] = file_path
return files
@pytest.fixture(scope="class")
def ragflow_tmp_dir(request: FixtureRequest, tmp_path_factory: Path) -> Path:
class_name = request.cls.__name__
return tmp_path_factory.mktemp(class_name)
@pytest.fixture(scope="session")
def client(token: str) -> RAGFlow:
return RAGFlow(api_key=token, base_url=HOST_ADDRESS, version=VERSION)
@pytest.fixture(scope="function")
def clear_datasets(request: FixtureRequest, client: RAGFlow):
def cleanup():
delete_all_datasets(client)
request.addfinalizer(cleanup)
@pytest.fixture(scope="function")
def clear_chat_assistants(request: FixtureRequest, client: RAGFlow):
def cleanup():
delete_all_chats(client)
request.addfinalizer(cleanup)
@pytest.fixture(scope="function")
def clear_session_with_chat_assistants(request, add_chat_assistants):
def cleanup():
for chat_assistant in chat_assistants:
try:
delete_all_sessions(chat_assistant)
except Exception:
pass
request.addfinalizer(cleanup)
_, _, chat_assistants = add_chat_assistants
@pytest.fixture(scope="class")
def add_dataset(request: FixtureRequest, client: RAGFlow) -> DataSet:
def cleanup():
delete_all_datasets(client)
request.addfinalizer(cleanup)
return batch_create_datasets(client, 1)[0]
@pytest.fixture(scope="function")
def add_dataset_func(request: FixtureRequest, client: RAGFlow) -> DataSet:
def cleanup():
delete_all_datasets(client)
request.addfinalizer(cleanup)
return batch_create_datasets(client, 1)[0]
@pytest.fixture(scope="class")
def add_document(add_dataset: DataSet, ragflow_tmp_dir: Path) -> tuple[DataSet, Document]:
return add_dataset, bulk_upload_documents(add_dataset, 1, ragflow_tmp_dir)[0]
@pytest.fixture(scope="class")
def add_chunks(request: FixtureRequest, add_document: tuple[DataSet, Document]) -> tuple[DataSet, Document, list[Chunk]]:
def cleanup():
try:
delete_all_chunks(document)
except Exception:
pass
request.addfinalizer(cleanup)
dataset, document = add_document
dataset.async_parse_documents([document.id])
condition(dataset)
chunks = batch_add_chunks(document, 4)
# issues/6487
sleep(1)
return dataset, document, chunks
@pytest.fixture(scope="class")
def add_chat_assistants(request, client, add_document) -> tuple[DataSet, Document, list[Chat]]:
def cleanup():
try:
delete_all_chats(client)
except Exception:
pass
request.addfinalizer(cleanup)
dataset, document = add_document
dataset.async_parse_documents([document.id])
condition(dataset)
return dataset, document, batch_create_chat_assistants(client, 5)