Refactor: Consolidation WEB API & HTTP API for document infos (infiniflow#14239)

### What problem does this PR solve?

Before consolidation
Web API: POST /v1/document/infos
Http API - GET /api/v1/datasets/<dataset_id>/documents

After consolidation, Restful API -- GET
/api/v1/datasets/<dataset_id>/documents?ids=id1&ids=id2

### Type of change

- [ ] Refactoring

Author: xugangqiang

api/apps/document_app.py

@@ -183,22 +183,6 @@ async def create():
         return server_error_response(e)
 
 
-@manager.route("/infos", methods=["POST"])  # noqa: F821
-@login_required
-async def doc_infos():
-    req = await get_request_json()
-    doc_ids = req["doc_ids"]
-    for doc_id in doc_ids:
-        if not DocumentService.accessible(doc_id, current_user.id):
-            return get_json_result(data=False, message="No authorization.", code=RetCode.AUTHENTICATION_ERROR)
-    docs = DocumentService.get_by_ids(doc_ids)
-    docs_list = list(docs.dicts())
-    # Add meta_fields for each document
-    for doc in docs_list:
-        doc["meta_fields"] = DocMetadataService.get_document_metadata(doc["id"])
-    return get_json_result(data=docs_list)
-
-
 @manager.route("/metadata/update", methods=["POST"])  # noqa: F821
 @login_required
 @validate_request("doc_ids")

api/apps/restful_apis/document_api.py

@@ -527,6 +527,12 @@ def _get_docs_with_request(req, dataset_id:str):
     if doc_name and not DocumentService.query(name=doc_name, kb_id=dataset_id):
         return RetCode.DATA_ERROR, f"You don't own the document {doc_name}.", [], 0
 
+    doc_ids = q.getlist("ids")
+    if doc_id and len(doc_ids) > 0:
+        return RetCode.DATA_ERROR, f"Should not provide both 'id':{doc_id} and 'ids'{doc_ids}"
+    if len(doc_ids) > 0:
+        doc_ids_filter = doc_ids
+
     docs, total = DocumentService.get_by_kb_id(dataset_id, page, page_size, orderby, desc, keywords, run_status_converted, types, suffix,
                                                name=doc_name, doc_ids=doc_ids_filter, return_empty_metadata=return_empty_metadata)
 

sdk/python/ragflow_sdk/modules/dataset.py

@@ -66,6 +66,7 @@ def upload_documents(self, document_list: list[dict]):
     def list_documents(
         self,
         id: str | None = None,
+        ids: list[str] | None = None,
         name: str | None = None,
         keywords: str | None = None,
         page: int = 1,
@@ -75,6 +76,10 @@ def list_documents(
         create_time_from: int = 0,
         create_time_to: int = 0,
     ):
+        # Validate that id and ids are not used together
+        if id and ids:
+            raise ValueError("Cannot use both 'id' and 'ids' parameters at the same time.")
+        
         params = {
             "id": id,
             "name": name,
@@ -86,6 +91,10 @@ def list_documents(
             "create_time_from": create_time_from,
             "create_time_to": create_time_to,
         }
+        # Handle ids parameter - convert to multiple query params
+        if ids:
+            for doc_id in ids:
+                params.append(("ids", doc_id))
         res = self.get(f"/datasets/{self.id}/documents", params=params)
         res = res.json()
         documents = []

sdk/python/test/test_frontend_api/common.py

@@ -75,11 +75,36 @@ def list_document(auth, dataset_id):
     return res.json()
 
 
-def get_docs_info(auth, doc_ids):
+def get_docs_info(auth, dataset_id, doc_ids=None, doc_id=None):
+    """
+    Get document information by IDs.
+    
+    Args:
+        auth: Authorization header
+        dataset_id: Dataset ID
+        doc_ids: List of document IDs (use for multiple) - exclusive with doc_id
+        doc_id: Single document ID (use for one) - exclusive with doc_ids
+    
+    Raises:
+        ValueError: If both doc_id and doc_ids are provided
+    """
+    # Validate that id and ids are not used together
+    if doc_id and doc_ids:
+        raise ValueError("Cannot use both 'id' and 'ids' parameters at the same time.")
+    
     authorization = {"Authorization": auth}
-    json_req = {"doc_ids": doc_ids}
-    url = f"{HOST_ADDRESS}/v1/document/infos"
-    res = requests.post(url=url, headers=authorization, json=json_req)
+    params = {}
+    if doc_ids:
+        # Multiple IDs
+        for id in doc_ids:
+            params.append(("ids", id))
+    elif doc_id:
+        # Single ID
+        params["id"] = doc_id
+    
+    # Use /api/v1 prefix for dataset API
+    url = f"{HOST_ADDRESS}/api/v1/datasets/{dataset_id}/documents"
+    res = requests.get(url=url, headers=authorization, params=params)
     return res.json()
 
 

sdk/python/test/test_frontend_api/test_chunk.py

@@ -48,14 +48,14 @@ def test_parse_txt_document(get_auth):
     for doc in res['data']['docs']:
         doc_id_list.append(doc['id'])
 
-    res = get_docs_info(get_auth, doc_id_list)
+    res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
     print(doc_id_list)
     doc_count = len(doc_id_list)
     res = parse_docs(get_auth, doc_id_list)
 
     start_ts = timer()
     while True:
-        res = get_docs_info(get_auth, doc_id_list)
+        res = get_docs_info(get_auth, dataset_id, doc_ids=doc_id_list)
         finished_count = 0
         for doc_info in res['data']:
             if doc_info['progress'] == 1:

test/testcases/test_web_api/test_common.py

@@ -397,8 +397,8 @@ def document_filter(auth, dataset_id, payload=None, *, headers=HEADERS, data=Non
     return res.json()
 
 
-def document_infos(auth, payload=None, *, headers=HEADERS, data=None):
-    res = requests.post(url=f"{HOST_ADDRESS}{DOCUMENT_APP_URL}/infos", headers=headers, auth=auth, json=payload, data=data)
+def document_infos(auth, dataset_id, params=None, payload=None, *, headers=HEADERS, data=None):
+    res = requests.get(url=f"{HOST_ADDRESS}{DATASETS_URL}/{dataset_id}/documents", params=params, json=payload, headers=headers, auth=auth, data=data)
     return res.json()
 
 

test/testcases/test_web_api/test_document_app/test_document_metadata.py

@@ -44,7 +44,7 @@ def test_filter_auth_invalid(self, invalid_auth, expected_code, expected_fragmen
     @pytest.mark.p2
     @pytest.mark.parametrize("invalid_auth, expected_code, expected_fragment", INVALID_AUTH_CASES)
     def test_infos_auth_invalid(self, invalid_auth, expected_code, expected_fragment):
-        res = document_infos(invalid_auth, {"doc_ids": ["doc_id"]})
+        res = document_infos(invalid_auth, "kb_id", {"doc_ids": ["doc_id"]})
         assert res["code"] == expected_code, res
         assert expected_fragment in res["message"], res
 
@@ -91,11 +91,12 @@ def test_filter(self, WebApiAuth, add_dataset_func):
 
     @pytest.mark.p2
     def test_infos(self, WebApiAuth, add_document_func):
-        _, doc_id = add_document_func
-        res = document_infos(WebApiAuth, {"doc_ids": [doc_id]})
+        dataset_id, doc_id = add_document_func
+        res = document_infos(WebApiAuth, dataset_id, {"ids": [doc_id]})
         assert res["code"] == 0, res
-        assert len(res["data"]) == 1, res
-        assert res["data"][0]["id"] == doc_id, res
+        docs = res["data"]["docs"]
+        assert len(docs) == 1, docs
+        assert docs[0]["id"] == doc_id, res
 
     ## The inputs has been changed to add 'doc_ids'
     ## TODO: 
@@ -138,20 +139,22 @@ def test_infos(self, WebApiAuth, add_document_func):
 
     @pytest.mark.p2
     def test_change_status(self, WebApiAuth, add_document_func):
-        _, doc_id = add_document_func
+        dataset_id, doc_id = add_document_func
         res = document_change_status(WebApiAuth, {"doc_ids": [doc_id], "status": "1"})
+
         assert res["code"] == 0, res
         assert res["data"][doc_id]["status"] == "1", res
-        info_res = document_infos(WebApiAuth, {"doc_ids": [doc_id]})
+        info_res = document_infos(WebApiAuth, dataset_id, {"ids": [doc_id]})
+
         assert info_res["code"] == 0, info_res
-        assert info_res["data"][0]["status"] == "1", info_res
+        assert info_res["data"]["docs"][0]["status"] == "1", info_res
 
 
 class TestDocumentMetadataNegative:
     @pytest.mark.p2
     def test_filter_missing_kb_id(self, WebApiAuth, add_document_func):
         kb_id, doc_id = add_document_func
-        res = document_filter(WebApiAuth, "", {"doc_ids": [doc_id]})
+        res = document_filter(WebApiAuth, "", {"ids": [doc_id]})
         assert res["code"] == 100, res
         assert "<MethodNotAllowed '405: Method Not Allowed'>" == res["message"], res
 
@@ -228,26 +231,6 @@ def _allow_kb(self, module, monkeypatch, kb_id="kb1", tenant_id="tenant1"):
         monkeypatch.setattr(module.UserTenantService, "query", lambda **_kwargs: [SimpleNamespace(tenant_id=tenant_id)])
         monkeypatch.setattr(module.KnowledgebaseService, "query", lambda **_kwargs: True if _kwargs.get("id") == kb_id else False)
 
-
-    def test_infos_meta_fields(self, document_app_module, monkeypatch):
-        module = document_app_module
-        monkeypatch.setattr(module.DocumentService, "accessible", lambda *_args, **_kwargs: True)
-
-        class _Docs:
-            def dicts(self):
-                return [{"id": "doc1"}]
-
-        monkeypatch.setattr(module.DocumentService, "get_by_ids", lambda _ids: _Docs())
-        monkeypatch.setattr(module.DocMetadataService, "get_document_metadata", lambda _doc_id: {"author": "alice"})
-
-        async def fake_request_json():
-            return {"doc_ids": ["doc1"]}
-
-        monkeypatch.setattr(module, "get_request_json", fake_request_json)
-        res = _run(module.doc_infos())
-        assert res["code"] == 0
-        assert res["data"][0]["meta_fields"]["author"] == "alice"
-
     def test_metadata_update_missing_kb_id(self, document_app_module, monkeypatch):
         module = document_app_module
 

web/src/services/knowledge-service.ts

@@ -34,7 +34,6 @@ const {
   documentUpload,
   webCrawl,
   knowledgeGraph,
-  documentInfos,
   listTagByKnowledgeIds,
   setMeta,
   getMeta,
@@ -101,10 +100,6 @@ const methods = {
     url: webCrawl,
     method: 'post',
   },
-  documentInfos: {
-    url: documentInfos,
-    method: 'post',
-  },
   setMeta: {
     url: setMeta,
     method: 'post',

web/src/utils/api.ts

@@ -123,7 +123,6 @@ export default {
   documentUpload: (datasetId: string) =>
     `${restAPIv1}/datasets/${datasetId}/documents`,
   webCrawl: `${webAPI}/document/web_crawl`,
-  documentInfos: `${webAPI}/document/infos`,
   uploadAndParse: `${webAPI}/document/upload_info`,
   setMeta: `${webAPI}/document/set_meta`,
   getDatasetFilter: (datasetId: string) =>