feat(api): add child chunk management endpoints for segments in dataset API
This commit is contained in:
ZeroZ_JQ
parent
8b55d42239
commit
9b522bd820
@ -13,10 +13,16 @@ from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
|
|||||||
from core.model_manager import ModelManager
|
from core.model_manager import ModelManager
|
||||||
from core.model_runtime.entities.model_entities import ModelType
|
from core.model_runtime.entities.model_entities import ModelType
|
||||||
from extensions.ext_database import db
|
from extensions.ext_database import db
|
||||||
from fields.segment_fields import segment_fields
|
from fields.segment_fields import segment_fields, child_chunk_fields
|
||||||
from models.dataset import Dataset, DocumentSegment
|
from models.dataset import Dataset, DocumentSegment, ChildChunk
|
||||||
from services.dataset_service import DatasetService, DocumentService, SegmentService
|
from services.dataset_service import DatasetService, DocumentService, SegmentService
|
||||||
from services.entities.knowledge_entities.knowledge_entities import SegmentUpdateArgs
|
from services.entities.knowledge_entities.knowledge_entities import SegmentUpdateArgs
|
||||||
|
from services.errors.chunk import (
|
||||||
|
ChildChunkDeleteIndexError as ChildChunkDeleteIndexServiceError,
|
||||||
|
ChildChunkIndexingError as ChildChunkIndexingServiceError,
|
||||||
|
ChildChunkIndexingError,
|
||||||
|
ChildChunkDeleteIndexError
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class SegmentApi(DatasetApiResource):
|
class SegmentApi(DatasetApiResource):
|
||||||
@ -195,7 +201,210 @@ class DatasetSegmentApi(DatasetApiResource):
|
|||||||
return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
|
return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
|
||||||
|
|
||||||
|
|
||||||
|
class ChildChunkAddApi(DatasetApiResource):
|
||||||
|
"""Resource for child chunks."""
|
||||||
|
|
||||||
|
@cloud_edition_billing_resource_check("vector_space", "dataset")
|
||||||
|
@cloud_edition_billing_knowledge_limit_check("add_segment", "dataset")
|
||||||
|
def post(self, tenant_id, dataset_id, document_id, segment_id):
|
||||||
|
"""Create child chunk."""
|
||||||
|
# check dataset
|
||||||
|
dataset_id = str(dataset_id)
|
||||||
|
tenant_id = str(tenant_id)
|
||||||
|
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
|
||||||
|
if not dataset:
|
||||||
|
raise NotFound("Dataset not found.")
|
||||||
|
|
||||||
|
# check document
|
||||||
|
document_id = str(document_id)
|
||||||
|
document = DocumentService.get_document(dataset.id, document_id)
|
||||||
|
if not document:
|
||||||
|
raise NotFound("Document not found.")
|
||||||
|
|
||||||
|
# check segment
|
||||||
|
segment_id = str(segment_id)
|
||||||
|
segment = DocumentSegment.query.filter(
|
||||||
|
DocumentSegment.id == str(segment_id),
|
||||||
|
DocumentSegment.tenant_id == current_user.current_tenant_id
|
||||||
|
).first()
|
||||||
|
if not segment:
|
||||||
|
raise NotFound("Segment not found.")
|
||||||
|
|
||||||
|
# check embedding model setting
|
||||||
|
if dataset.indexing_technique == "high_quality":
|
||||||
|
try:
|
||||||
|
model_manager = ModelManager()
|
||||||
|
model_manager.get_model_instance(
|
||||||
|
tenant_id=current_user.current_tenant_id,
|
||||||
|
provider=dataset.embedding_model_provider,
|
||||||
|
model_type=ModelType.TEXT_EMBEDDING,
|
||||||
|
model=dataset.embedding_model,
|
||||||
|
)
|
||||||
|
except LLMBadRequestError:
|
||||||
|
raise ProviderNotInitializeError(
|
||||||
|
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
|
||||||
|
)
|
||||||
|
except ProviderTokenNotInitError as ex:
|
||||||
|
raise ProviderNotInitializeError(ex.description)
|
||||||
|
|
||||||
|
# validate args
|
||||||
|
parser = reqparse.RequestParser()
|
||||||
|
parser.add_argument("content", type=str, required=True, nullable=False, location="json")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
try:
|
||||||
|
child_chunk = SegmentService.create_child_chunk(args.get("content"), segment, document, dataset)
|
||||||
|
except ChildChunkIndexingServiceError as e:
|
||||||
|
raise ChildChunkIndexingError(str(e))
|
||||||
|
|
||||||
|
return {"data": marshal(child_chunk, child_chunk_fields)}, 200
|
||||||
|
|
||||||
|
def get(self, tenant_id, dataset_id, document_id, segment_id):
|
||||||
|
"""Get child chunks."""
|
||||||
|
# check dataset
|
||||||
|
dataset_id = str(dataset_id)
|
||||||
|
tenant_id = str(tenant_id)
|
||||||
|
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
|
||||||
|
if not dataset:
|
||||||
|
raise NotFound("Dataset not found.")
|
||||||
|
|
||||||
|
# check document
|
||||||
|
document_id = str(document_id)
|
||||||
|
document = DocumentService.get_document(dataset.id, document_id)
|
||||||
|
if not document:
|
||||||
|
raise NotFound("Document not found.")
|
||||||
|
|
||||||
|
# check segment
|
||||||
|
segment_id = str(segment_id)
|
||||||
|
segment = DocumentSegment.query.filter(
|
||||||
|
DocumentSegment.id == str(segment_id),
|
||||||
|
DocumentSegment.tenant_id == current_user.current_tenant_id
|
||||||
|
).first()
|
||||||
|
if not segment:
|
||||||
|
raise NotFound("Segment not found.")
|
||||||
|
|
||||||
|
parser = reqparse.RequestParser()
|
||||||
|
parser.add_argument("limit", type=int, default=20, location="args")
|
||||||
|
parser.add_argument("keyword", type=str, default=None, location="args")
|
||||||
|
parser.add_argument("page", type=int, default=1, location="args")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
page = args["page"]
|
||||||
|
limit = min(args["limit"], 100)
|
||||||
|
keyword = args["keyword"]
|
||||||
|
|
||||||
|
child_chunks = SegmentService.get_child_chunks(segment_id, document_id, dataset_id, page, limit, keyword)
|
||||||
|
|
||||||
|
return {
|
||||||
|
"data": marshal(child_chunks.items, child_chunk_fields),
|
||||||
|
"total": child_chunks.total,
|
||||||
|
"total_pages": child_chunks.pages,
|
||||||
|
"page": page,
|
||||||
|
"limit": limit,
|
||||||
|
}, 200
|
||||||
|
|
||||||
|
|
||||||
|
class ChildChunkUpdateApi(DatasetApiResource):
|
||||||
|
"""Resource for updating child chunks."""
|
||||||
|
|
||||||
|
def delete(self, tenant_id, dataset_id, document_id, segment_id, child_chunk_id):
|
||||||
|
"""Delete child chunk."""
|
||||||
|
# check dataset
|
||||||
|
dataset_id = str(dataset_id)
|
||||||
|
tenant_id = str(tenant_id)
|
||||||
|
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
|
||||||
|
if not dataset:
|
||||||
|
raise NotFound("Dataset not found.")
|
||||||
|
|
||||||
|
# check document
|
||||||
|
document_id = str(document_id)
|
||||||
|
document = DocumentService.get_document(dataset.id, document_id)
|
||||||
|
if not document:
|
||||||
|
raise NotFound("Document not found.")
|
||||||
|
|
||||||
|
# check segment
|
||||||
|
segment_id = str(segment_id)
|
||||||
|
segment = DocumentSegment.query.filter(
|
||||||
|
DocumentSegment.id == str(segment_id),
|
||||||
|
DocumentSegment.tenant_id == current_user.current_tenant_id
|
||||||
|
).first()
|
||||||
|
if not segment:
|
||||||
|
raise NotFound("Segment not found.")
|
||||||
|
|
||||||
|
# check child chunk
|
||||||
|
child_chunk_id = str(child_chunk_id)
|
||||||
|
child_chunk = ChildChunk.query.filter(
|
||||||
|
ChildChunk.id == str(child_chunk_id),
|
||||||
|
ChildChunk.tenant_id == current_user.current_tenant_id
|
||||||
|
).first()
|
||||||
|
if not child_chunk:
|
||||||
|
raise NotFound("Child chunk not found.")
|
||||||
|
|
||||||
|
try:
|
||||||
|
SegmentService.delete_child_chunk(child_chunk, dataset)
|
||||||
|
except ChildChunkDeleteIndexServiceError as e:
|
||||||
|
raise ChildChunkDeleteIndexError(str(e))
|
||||||
|
|
||||||
|
return {"result": "success"}, 200
|
||||||
|
|
||||||
|
@cloud_edition_billing_resource_check("vector_space", "dataset")
|
||||||
|
def patch(self, tenant_id, dataset_id, document_id, segment_id, child_chunk_id):
|
||||||
|
"""Update child chunk."""
|
||||||
|
# check dataset
|
||||||
|
dataset_id = str(dataset_id)
|
||||||
|
tenant_id = str(tenant_id)
|
||||||
|
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
|
||||||
|
if not dataset:
|
||||||
|
raise NotFound("Dataset not found.")
|
||||||
|
|
||||||
|
# check document
|
||||||
|
document_id = str(document_id)
|
||||||
|
document = DocumentService.get_document(dataset.id, document_id)
|
||||||
|
if not document:
|
||||||
|
raise NotFound("Document not found.")
|
||||||
|
|
||||||
|
# check segment
|
||||||
|
segment_id = str(segment_id)
|
||||||
|
segment = DocumentSegment.query.filter(
|
||||||
|
DocumentSegment.id == str(segment_id),
|
||||||
|
DocumentSegment.tenant_id == current_user.current_tenant_id
|
||||||
|
).first()
|
||||||
|
if not segment:
|
||||||
|
raise NotFound("Segment not found.")
|
||||||
|
|
||||||
|
# check child chunk
|
||||||
|
child_chunk_id = str(child_chunk_id)
|
||||||
|
child_chunk = ChildChunk.query.filter(
|
||||||
|
ChildChunk.id == str(child_chunk_id),
|
||||||
|
ChildChunk.tenant_id == current_user.current_tenant_id
|
||||||
|
).first()
|
||||||
|
if not child_chunk:
|
||||||
|
raise NotFound("Child chunk not found.")
|
||||||
|
|
||||||
|
# validate args
|
||||||
|
parser = reqparse.RequestParser()
|
||||||
|
parser.add_argument("content", type=str, required=True, nullable=False, location="json")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
try:
|
||||||
|
child_chunk = SegmentService.update_child_chunk(
|
||||||
|
args.get("content"), child_chunk, segment, document, dataset
|
||||||
|
)
|
||||||
|
except ChildChunkIndexingServiceError as e:
|
||||||
|
raise ChildChunkIndexingError(str(e))
|
||||||
|
|
||||||
|
return {"data": marshal(child_chunk, child_chunk_fields)}, 200
|
||||||
|
|
||||||
|
|
||||||
api.add_resource(SegmentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments")
|
api.add_resource(SegmentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments")
|
||||||
api.add_resource(
|
api.add_resource(
|
||||||
DatasetSegmentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>"
|
DatasetSegmentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>"
|
||||||
)
|
)
|
||||||
|
api.add_resource(
|
||||||
|
ChildChunkAddApi,
|
||||||
|
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks"
|
||||||
|
)
|
||||||
|
api.add_resource(
|
||||||
|
ChildChunkUpdateApi,
|
||||||
|
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks/<uuid:child_chunk_id>"
|
||||||
|
)
|
||||||
|
|||||||
1
move_section.js
Normal file
1
move_section.js
Normal file
@ -0,0 +1 @@
|
|||||||
|
const fs = require("fs"); const path = require("path"); const filePath = path.join(process.cwd(), "web/app/(commonLayout)/datasets/template/template.zh.mdx"); let content = fs.readFileSync(filePath, "utf8"); const lines = content.split("\n"); const retrievalSection = lines.slice(1234, 1335).join("\n"); content = lines.slice(0, 1234).concat(lines.slice(1335)).join("\n"); content += "\n\n" + retrievalSection; fs.writeFileSync(filePath, content);
|
||||||
@ -881,182 +881,10 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
|
|||||||
|
|
||||||
<hr className='ml-0 mr-0' />
|
<hr className='ml-0 mr-0' />
|
||||||
|
|
||||||
<Heading
|
|
||||||
url='/datasets/{dataset_id}/documents/{batch}/indexing-status'
|
|
||||||
method='GET'
|
|
||||||
title='获取文档嵌入状态（进度）'
|
|
||||||
name='#indexing_status'
|
|
||||||
/>
|
|
||||||
<Row>
|
|
||||||
<Col>
|
|
||||||
### Path
|
|
||||||
<Properties>
|
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
||||||
知识库 ID
|
|
||||||
</Property>
|
|
||||||
<Property name='batch' type='string' key='batch'>
|
|
||||||
上传文档的批次号
|
|
||||||
</Property>
|
|
||||||
</Properties>
|
|
||||||
</Col>
|
|
||||||
<Col sticky>
|
|
||||||
<CodeGroup
|
|
||||||
title="Request"
|
|
||||||
tag="GET"
|
|
||||||
label="/datasets/{dataset_id}/documents/{batch}/indexing-status"
|
|
||||||
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{batch}/indexing-status' \\\n--header 'Authorization: Bearer {api_key}'`}
|
|
||||||
>
|
|
||||||
```bash {{ title: 'cURL' }}
|
|
||||||
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{batch}/indexing-status' \
|
|
||||||
--header 'Authorization: Bearer {api_key}' \
|
|
||||||
```
|
|
||||||
</CodeGroup>
|
|
||||||
<CodeGroup title="Response">
|
|
||||||
```json {{ title: 'Response' }}
|
|
||||||
{
|
|
||||||
"data":[{
|
|
||||||
"id": "",
|
|
||||||
"indexing_status": "indexing",
|
|
||||||
"processing_started_at": 1681623462.0,
|
|
||||||
"parsing_completed_at": 1681623462.0,
|
|
||||||
"cleaning_completed_at": 1681623462.0,
|
|
||||||
"splitting_completed_at": 1681623462.0,
|
|
||||||
"completed_at": null,
|
|
||||||
"paused_at": null,
|
|
||||||
"error": null,
|
|
||||||
"stopped_at": null,
|
|
||||||
"completed_segments": 24,
|
|
||||||
"total_segments": 100
|
|
||||||
}]
|
|
||||||
}
|
|
||||||
```
|
|
||||||
</CodeGroup>
|
|
||||||
</Col>
|
|
||||||
</Row>
|
|
||||||
|
|
||||||
<hr className='ml-0 mr-0' />
|
|
||||||
|
|
||||||
<Heading
|
|
||||||
url='/datasets/{dataset_id}/documents/{document_id}'
|
|
||||||
method='DELETE'
|
|
||||||
title='删除文档'
|
|
||||||
name='#delete_document'
|
|
||||||
/>
|
|
||||||
<Row>
|
|
||||||
<Col>
|
|
||||||
### Path
|
|
||||||
<Properties>
|
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
||||||
知识库 ID
|
|
||||||
</Property>
|
|
||||||
<Property name='document_id' type='string' key='document_id'>
|
|
||||||
文档 ID
|
|
||||||
</Property>
|
|
||||||
</Properties>
|
|
||||||
</Col>
|
|
||||||
<Col sticky>
|
|
||||||
<CodeGroup
|
|
||||||
title="Request"
|
|
||||||
tag="DELETE"
|
|
||||||
label="/datasets/{dataset_id}/documents/{document_id}"
|
|
||||||
targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
|
|
||||||
>
|
|
||||||
```bash {{ title: 'cURL' }}
|
|
||||||
curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}' \
|
|
||||||
--header 'Authorization: Bearer {api_key}' \
|
|
||||||
```
|
|
||||||
</CodeGroup>
|
|
||||||
<CodeGroup title="Response">
|
|
||||||
```json {{ title: 'Response' }}
|
|
||||||
{
|
|
||||||
"result": "success"
|
|
||||||
}
|
|
||||||
```
|
|
||||||
</CodeGroup>
|
|
||||||
</Col>
|
|
||||||
</Row>
|
|
||||||
|
|
||||||
<hr className='ml-0 mr-0' />
|
|
||||||
|
|
||||||
<Heading
|
|
||||||
url='/datasets/{dataset_id}/documents'
|
|
||||||
method='GET'
|
|
||||||
title='知识库文档列表'
|
|
||||||
name='#dataset_document_list'
|
|
||||||
/>
|
|
||||||
<Row>
|
|
||||||
<Col>
|
|
||||||
### Path
|
|
||||||
<Properties>
|
|
||||||
<Property name='dataset_id' type='string' key='dataset_id'>
|
|
||||||
知识库 ID
|
|
||||||
</Property>
|
|
||||||
</Properties>
|
|
||||||
|
|
||||||
### Query
|
|
||||||
<Properties>
|
|
||||||
<Property name='keyword' type='string' key='keyword'>
|
|
||||||
搜索关键词，可选，目前仅搜索文档名称
|
|
||||||
</Property>
|
|
||||||
<Property name='page' type='string' key='page'>
|
|
||||||
页码，可选
|
|
||||||
</Property>
|
|
||||||
<Property name='limit' type='string' key='limit'>
|
|
||||||
返回条数，可选，默认 20，范围 1-100
|
|
||||||
</Property>
|
|
||||||
</Properties>
|
|
||||||
</Col>
|
|
||||||
<Col sticky>
|
|
||||||
<CodeGroup
|
|
||||||
title="Request"
|
|
||||||
tag="GET"
|
|
||||||
label="/datasets/{dataset_id}/documents"
|
|
||||||
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents' \\\n--header 'Authorization: Bearer {api_key}'`}
|
|
||||||
>
|
|
||||||
```bash {{ title: 'cURL' }}
|
|
||||||
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents' \
|
|
||||||
--header 'Authorization: Bearer {api_key}' \
|
|
||||||
```
|
|
||||||
</CodeGroup>
|
|
||||||
<CodeGroup title="Response">
|
|
||||||
```json {{ title: 'Response' }}
|
|
||||||
{
|
|
||||||
"data": [
|
|
||||||
{
|
|
||||||
"id": "",
|
|
||||||
"position": 1,
|
|
||||||
"data_source_type": "file_upload",
|
|
||||||
"data_source_info": null,
|
|
||||||
"dataset_process_rule_id": null,
|
|
||||||
"name": "dify",
|
|
||||||
"created_from": "",
|
|
||||||
"created_by": "",
|
|
||||||
"created_at": 1681623639,
|
|
||||||
"tokens": 0,
|
|
||||||
"indexing_status": "waiting",
|
|
||||||
"error": null,
|
|
||||||
"enabled": true,
|
|
||||||
"disabled_at": null,
|
|
||||||
"disabled_by": null,
|
|
||||||
"archived": false
|
|
||||||
},
|
|
||||||
],
|
|
||||||
"has_more": false,
|
|
||||||
"limit": 20,
|
|
||||||
"total": 9,
|
|
||||||
"page": 1
|
|
||||||
}
|
|
||||||
```
|
|
||||||
</CodeGroup>
|
|
||||||
</Col>
|
|
||||||
</Row>
|
|
||||||
|
|
||||||
<hr className='ml-0 mr-0' />
|
|
||||||
|
|
||||||
<Heading
|
<Heading
|
||||||
url='/datasets/{dataset_id}/documents/{document_id}/segments'
|
url='/datasets/{dataset_id}/documents/{document_id}/segments'
|
||||||
method='POST'
|
method='POST'
|
||||||
title='新增分段'
|
title='新增文档分段'
|
||||||
name='#create_new_segment'
|
name='#create_new_segment'
|
||||||
/>
|
/>
|
||||||
<Row>
|
<Row>
|
||||||
@ -1351,6 +1179,311 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
|
|||||||
</Col>
|
</Col>
|
||||||
</Row>
|
</Row>
|
||||||
|
|
||||||
|
|
||||||
|
<hr className='ml-0 mr-0' />
|
||||||
|
|
||||||
|
<Heading
|
||||||
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks'
|
||||||
|
method='POST'
|
||||||
|
title='新增文档子分段'
|
||||||
|
name='#create_child_chunk'
|
||||||
|
/>
|
||||||
|
<Row>
|
||||||
|
<Col>
|
||||||
|
### Path
|
||||||
|
<Properties>
|
||||||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
|
知识库 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='document_id' type='string' key='document_id'>
|
||||||
|
文档 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='segment_id' type='string' key='segment_id'>
|
||||||
|
分段 ID
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
|
||||||
|
### Request Body
|
||||||
|
<Properties>
|
||||||
|
<Property name='content' type='string' key='content'>
|
||||||
|
子分段内容
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
</Col>
|
||||||
|
<Col sticky>
|
||||||
|
<CodeGroup
|
||||||
|
title="Request"
|
||||||
|
tag="POST"
|
||||||
|
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks"
|
||||||
|
targetCode={`curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"content": "子分段内容"}'`}
|
||||||
|
>
|
||||||
|
```bash {{ title: 'cURL' }}
|
||||||
|
curl --location --request POST '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks' \
|
||||||
|
--header 'Authorization: Bearer {api_key}' \
|
||||||
|
--header 'Content-Type: application/json' \
|
||||||
|
--data-raw '{
|
||||||
|
"content": "子分段内容"
|
||||||
|
}'
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
<CodeGroup title="Response">
|
||||||
|
```json {{ title: 'Response' }}
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"id": "",
|
||||||
|
"segment_id": "",
|
||||||
|
"content": "子分段内容",
|
||||||
|
"word_count": 25,
|
||||||
|
"tokens": 0,
|
||||||
|
"index_node_id": "",
|
||||||
|
"index_node_hash": "",
|
||||||
|
"status": "completed",
|
||||||
|
"created_by": "",
|
||||||
|
"created_at": 1695312007,
|
||||||
|
"indexing_at": 1695312007,
|
||||||
|
"completed_at": 1695312007,
|
||||||
|
"error": null,
|
||||||
|
"stopped_at": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
</Col>
|
||||||
|
</Row>
|
||||||
|
|
||||||
|
<hr className='ml-0 mr-0' />
|
||||||
|
|
||||||
|
<Heading
|
||||||
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks'
|
||||||
|
method='GET'
|
||||||
|
title='查询文档子分段'
|
||||||
|
name='#get_child_chunks'
|
||||||
|
/>
|
||||||
|
<Row>
|
||||||
|
<Col>
|
||||||
|
### Path
|
||||||
|
<Properties>
|
||||||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
|
知识库 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='document_id' type='string' key='document_id'>
|
||||||
|
文档 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='segment_id' type='string' key='segment_id'>
|
||||||
|
分段 ID
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
|
||||||
|
### Query
|
||||||
|
<Properties>
|
||||||
|
<Property name='keyword' type='string' key='keyword'>
|
||||||
|
搜索关键词（选填）
|
||||||
|
</Property>
|
||||||
|
<Property name='page' type='integer' key='page'>
|
||||||
|
页码（选填，默认1）
|
||||||
|
</Property>
|
||||||
|
<Property name='limit' type='integer' key='limit'>
|
||||||
|
每页数量（选填，默认20，最大100）
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
</Col>
|
||||||
|
<Col sticky>
|
||||||
|
<CodeGroup
|
||||||
|
title="Request"
|
||||||
|
tag="GET"
|
||||||
|
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks"
|
||||||
|
targetCode={`curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks?page=1&limit=20' \\\n--header 'Authorization: Bearer {api_key}'`}
|
||||||
|
>
|
||||||
|
```bash {{ title: 'cURL' }}
|
||||||
|
curl --location --request GET '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks?page=1&limit=20' \
|
||||||
|
--header 'Authorization: Bearer {api_key}'
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
<CodeGroup title="Response">
|
||||||
|
```json {{ title: 'Response' }}
|
||||||
|
{
|
||||||
|
"data": [{
|
||||||
|
"id": "",
|
||||||
|
"segment_id": "",
|
||||||
|
"content": "子分段内容",
|
||||||
|
"word_count": 25,
|
||||||
|
"tokens": 0,
|
||||||
|
"index_node_id": "",
|
||||||
|
"index_node_hash": "",
|
||||||
|
"status": "completed",
|
||||||
|
"created_by": "",
|
||||||
|
"created_at": 1695312007,
|
||||||
|
"indexing_at": 1695312007,
|
||||||
|
"completed_at": 1695312007,
|
||||||
|
"error": null,
|
||||||
|
"stopped_at": null
|
||||||
|
}],
|
||||||
|
"total": 1,
|
||||||
|
"total_pages": 1,
|
||||||
|
"page": 1,
|
||||||
|
"limit": 20
|
||||||
|
}
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
</Col>
|
||||||
|
</Row>
|
||||||
|
|
||||||
|
<hr className='ml-0 mr-0' />
|
||||||
|
|
||||||
|
<Heading
|
||||||
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}'
|
||||||
|
method='DELETE'
|
||||||
|
title='删除文档子分段'
|
||||||
|
name='#delete_child_chunk'
|
||||||
|
/>
|
||||||
|
<Row>
|
||||||
|
<Col>
|
||||||
|
### Path
|
||||||
|
<Properties>
|
||||||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
|
知识库 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='document_id' type='string' key='document_id'>
|
||||||
|
文档 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='segment_id' type='string' key='segment_id'>
|
||||||
|
分段 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='child_chunk_id' type='string' key='child_chunk_id'>
|
||||||
|
子分段 ID
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
</Col>
|
||||||
|
<Col sticky>
|
||||||
|
<CodeGroup
|
||||||
|
title="Request"
|
||||||
|
tag="DELETE"
|
||||||
|
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}"
|
||||||
|
targetCode={`curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}' \\\n--header 'Authorization: Bearer {api_key}'`}
|
||||||
|
>
|
||||||
|
```bash {{ title: 'cURL' }}
|
||||||
|
curl --location --request DELETE '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}' \
|
||||||
|
--header 'Authorization: Bearer {api_key}'
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
<CodeGroup title="Response">
|
||||||
|
```json {{ title: 'Response' }}
|
||||||
|
{
|
||||||
|
"result": "success"
|
||||||
|
}
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
</Col>
|
||||||
|
</Row>
|
||||||
|
|
||||||
|
<hr className='ml-0 mr-0' />
|
||||||
|
|
||||||
|
<Row>
|
||||||
|
<Col>
|
||||||
|
### 错误信息
|
||||||
|
<Properties>
|
||||||
|
<Property name='code' type='string' key='code'>
|
||||||
|
返回的错误代码
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
<Properties>
|
||||||
|
<Property name='status' type='number' key='status'>
|
||||||
|
返回的错误状态
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
<Properties>
|
||||||
|
<Property name='message' type='string' key='message'>
|
||||||
|
返回的错误信息
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
</Col>
|
||||||
|
<Col>
|
||||||
|
<CodeGroup title="Example">
|
||||||
|
```json {{ title: 'Response' }}
|
||||||
|
{
|
||||||
|
"code": "no_file_uploaded",
|
||||||
|
"message": "Please upload your file.",
|
||||||
|
"status": 400
|
||||||
|
}
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
</Col>
|
||||||
|
</Row>
|
||||||
|
|
||||||
|
<hr className='ml-0 mr-0' />
|
||||||
|
|
||||||
|
<Heading
|
||||||
|
url='/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}'
|
||||||
|
method='PATCH'
|
||||||
|
title='更新文档子分段'
|
||||||
|
name='#update_child_chunk'
|
||||||
|
/>
|
||||||
|
<Row>
|
||||||
|
<Col>
|
||||||
|
### Path
|
||||||
|
<Properties>
|
||||||
|
<Property name='dataset_id' type='string' key='dataset_id'>
|
||||||
|
知识库 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='document_id' type='string' key='document_id'>
|
||||||
|
文档 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='segment_id' type='string' key='segment_id'>
|
||||||
|
分段 ID
|
||||||
|
</Property>
|
||||||
|
<Property name='child_chunk_id' type='string' key='child_chunk_id'>
|
||||||
|
子分段 ID
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
|
||||||
|
### Request Body
|
||||||
|
<Properties>
|
||||||
|
<Property name='content' type='string' key='content'>
|
||||||
|
子分段内容
|
||||||
|
</Property>
|
||||||
|
</Properties>
|
||||||
|
</Col>
|
||||||
|
<Col sticky>
|
||||||
|
<CodeGroup
|
||||||
|
title="Request"
|
||||||
|
tag="PATCH"
|
||||||
|
label="/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}"
|
||||||
|
targetCode={`curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}' \\\n--header 'Authorization: Bearer {api_key}' \\\n--header 'Content-Type: application/json' \\\n--data-raw '{"content": "更新的子分段内容"}'`}
|
||||||
|
>
|
||||||
|
```bash {{ title: 'cURL' }}
|
||||||
|
curl --location --request PATCH '${props.apiBaseUrl}/datasets/{dataset_id}/documents/{document_id}/segments/{segment_id}/child_chunks/{child_chunk_id}' \
|
||||||
|
--header 'Authorization: Bearer {api_key}' \
|
||||||
|
--header 'Content-Type: application/json' \
|
||||||
|
--data-raw '{
|
||||||
|
"content": "更新的子分段内容"
|
||||||
|
}'
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
<CodeGroup title="Response">
|
||||||
|
```json {{ title: 'Response' }}
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"id": "",
|
||||||
|
"segment_id": "",
|
||||||
|
"content": "更新的子分段内容",
|
||||||
|
"word_count": 25,
|
||||||
|
"tokens": 0,
|
||||||
|
"index_node_id": "",
|
||||||
|
"index_node_hash": "",
|
||||||
|
"status": "completed",
|
||||||
|
"created_by": "",
|
||||||
|
"created_at": 1695312007,
|
||||||
|
"indexing_at": 1695312007,
|
||||||
|
"completed_at": 1695312007,
|
||||||
|
"error": null,
|
||||||
|
"stopped_at": null
|
||||||
|
}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
</CodeGroup>
|
||||||
|
</Col>
|
||||||
|
</Row>
|
||||||
|
|
||||||
<hr className='ml-0 mr-0' />
|
<hr className='ml-0 mr-0' />
|
||||||
|
|
||||||
<Heading
|
<Heading
|
||||||
@ -1548,39 +1681,7 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
|
|||||||
</Row>
|
</Row>
|
||||||
|
|
||||||
|
|
||||||
<hr className='ml-0 mr-0' />
|
|
||||||
|
|
||||||
<Row>
|
|
||||||
<Col>
|
|
||||||
### 错误信息
|
|
||||||
<Properties>
|
|
||||||
<Property name='code' type='string' key='code'>
|
|
||||||
返回的错误代码
|
|
||||||
</Property>
|
|
||||||
</Properties>
|
|
||||||
<Properties>
|
|
||||||
<Property name='status' type='number' key='status'>
|
|
||||||
返回的错误状态
|
|
||||||
</Property>
|
|
||||||
</Properties>
|
|
||||||
<Properties>
|
|
||||||
<Property name='message' type='string' key='message'>
|
|
||||||
返回的错误信息
|
|
||||||
</Property>
|
|
||||||
</Properties>
|
|
||||||
</Col>
|
|
||||||
<Col>
|
|
||||||
<CodeGroup title="Example">
|
|
||||||
```json {{ title: 'Response' }}
|
|
||||||
{
|
|
||||||
"code": "no_file_uploaded",
|
|
||||||
"message": "Please upload your file.",
|
|
||||||
"status": 400
|
|
||||||
}
|
|
||||||
```
|
|
||||||
</CodeGroup>
|
|
||||||
</Col>
|
|
||||||
</Row>
|
|
||||||
<table className="max-w-auto border-collapse border border-slate-400" style={{ maxWidth: 'none', width: 'auto' }}>
|
<table className="max-w-auto border-collapse border border-slate-400" style={{ maxWidth: 'none', width: 'auto' }}>
|
||||||
<thead style={{ background: '#f9fafc' }}>
|
<thead style={{ background: '#f9fafc' }}>
|
||||||
<tr>
|
<tr>
|
||||||
@ -1652,4 +1753,4 @@ import { Row, Col, Properties, Property, Heading, SubProperty, PropertyInstructi
|
|||||||
</tr>
|
</tr>
|
||||||
</tbody>
|
</tbody>
|
||||||
</table>
|
</table>
|
||||||
<div className="pb-4" />
|
<div className="pb-4" />
|
||||||
Loading…
Reference in New Issue
Block a user