From 9e258c495d802e9ec2f22b4184457c7b090ada8c Mon Sep 17 00:00:00 2001 From: jyong <718720800@qq.com> Date: Thu, 27 Feb 2025 15:30:37 +0800 Subject: [PATCH] dataset metadata fix --- api/controllers/console/datasets/datasets_document.py | 4 ++-- .../datasource/vdb/analyticdb/analyticdb_vector_sql.py | 8 ++++---- api/core/rag/datasource/vdb/baidu/baidu_vector.py | 4 ++-- api/core/rag/datasource/vdb/chroma/chroma_vector.py | 2 +- .../datasource/vdb/elasticsearch/elasticsearch_vector.py | 4 ++-- api/core/rag/datasource/vdb/lindorm/lindorm_vector.py | 4 ++-- api/core/rag/datasource/vdb/milvus/milvus_vector.py | 8 ++++---- api/core/rag/datasource/vdb/myscale/myscale_vector.py | 4 ++-- api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py | 4 ++-- .../rag/datasource/vdb/opensearch/opensearch_vector.py | 4 ++-- api/core/rag/datasource/vdb/oracle/oraclevector.py | 8 ++++---- api/core/rag/datasource/vdb/pgvecto_rs/pgvecto_rs.py | 2 +- api/core/rag/datasource/vdb/pgvector/pgvector.py | 8 ++++---- api/core/rag/datasource/vdb/qdrant/qdrant_vector.py | 4 ++-- api/core/rag/datasource/vdb/relyt/relyt_vector.py | 2 +- api/core/rag/datasource/vdb/tencent/tencent_vector.py | 2 +- .../vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py | 4 ++-- api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py | 4 ++-- api/core/rag/datasource/vdb/upstash/upstash_vector.py | 3 ++- api/core/rag/datasource/vdb/vikingdb/vikingdb_vector.py | 2 +- api/core/rag/datasource/vdb/weaviate/weaviate_vector.py | 4 ++-- 21 files changed, 45 insertions(+), 44 deletions(-) diff --git a/api/controllers/console/datasets/datasets_document.py b/api/controllers/console/datasets/datasets_document.py index 7ba9f5e121..efca753250 100644 --- a/api/controllers/console/datasets/datasets_document.py +++ b/api/controllers/console/datasets/datasets_document.py @@ -617,7 +617,7 @@ class DocumentDetailApi(DocumentResource): raise InvalidMetadataError(f"Invalid metadata value: {metadata}") if metadata == "only": - response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata} + response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata_details} elif metadata == "without": dataset_process_rules = DatasetService.get_process_rules(dataset_id) document_process_rules = document.dataset_process_rule.to_dict() @@ -678,7 +678,7 @@ class DocumentDetailApi(DocumentResource): "disabled_by": document.disabled_by, "archived": document.archived, "doc_type": document.doc_type, - "doc_metadata": document.doc_metadata, + "doc_metadata": document.doc_metadata_details, "segment_count": document.segment_count, "average_segment_length": document.average_segment_length, "hit_count": document.hit_count, diff --git a/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py b/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py index 884fc0e3eb..284896cce7 100644 --- a/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py +++ b/api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py @@ -197,8 +197,8 @@ class AnalyticdbVectorBySql: document_ids_filter = kwargs.get("document_ids_filter") where_clause = "WHERE 1=1" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause += f"AND metadata_->>'doc_id' IN ({doc_ids})" + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause += f"AND metadata_->>'document_id' IN ({document_ids})" score_threshold = float(kwargs.get("score_threshold") or 0.0) with self._get_cursor() as cur: query_vector_str = json.dumps(query_vector) @@ -228,8 +228,8 @@ class AnalyticdbVectorBySql: document_ids_filter = kwargs.get("document_ids_filter") where_clause = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause += f"AND metadata_->>'doc_id' IN ({doc_ids})" + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause += f"AND metadata_->>'document_id' IN ({document_ids})" with self._get_cursor() as cur: cur.execute( f"""SELECT id, vector, page_content, metadata_, diff --git a/api/core/rag/datasource/vdb/baidu/baidu_vector.py b/api/core/rag/datasource/vdb/baidu/baidu_vector.py index fd29166b1a..86f1f5bfe4 100644 --- a/api/core/rag/datasource/vdb/baidu/baidu_vector.py +++ b/api/core/rag/datasource/vdb/baidu/baidu_vector.py @@ -125,12 +125,12 @@ class BaiduVector(BaseVector): query_vector = [float(val) if isinstance(val, np.float64) else val for val in query_vector] document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) anns = AnnSearch( vector_field=self.field_vector, vector_floats=query_vector, params=HNSWSearchParams(ef=kwargs.get("ef", 10), limit=kwargs.get("top_k", 4)), - filter=f"doc_id IN ({doc_ids})", + filter=f"document_id IN ({document_ids})", ) else: anns = AnnSearch( diff --git a/api/core/rag/datasource/vdb/chroma/chroma_vector.py b/api/core/rag/datasource/vdb/chroma/chroma_vector.py index e101bf90c1..6c5619968e 100644 --- a/api/core/rag/datasource/vdb/chroma/chroma_vector.py +++ b/api/core/rag/datasource/vdb/chroma/chroma_vector.py @@ -100,7 +100,7 @@ class ChromaVector(BaseVector): results: QueryResult = collection.query( query_embeddings=query_vector, n_results=kwargs.get("top_k", 4), - where={"doc_id": {"$in": document_ids_filter}}, + where={"document_id": {"$in": document_ids_filter}}, ) else: results: QueryResult = collection.query(query_embeddings=query_vector, n_results=kwargs.get("top_k", 4)) diff --git a/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py b/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py index 93f5d8f547..117c6cbe22 100644 --- a/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py +++ b/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py @@ -119,7 +119,7 @@ class ElasticSearchVector(BaseVector): knn = {"field": Field.VECTOR.value, "query_vector": query_vector, "k": top_k, "num_candidates": num_candidates} document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - knn["filter"] = {"terms": {"metadata.doc_id": document_ids_filter}} + knn["filter"] = {"terms": {"metadata.document_id": document_ids_filter}} results = self._client.search(index=self._collection_name, knn=knn, size=top_k) @@ -150,7 +150,7 @@ class ElasticSearchVector(BaseVector): query_str = {"match": {Field.CONTENT_KEY.value: query}} document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - query_str["filter"] = {"terms": {"metadata.doc_id": document_ids_filter}} + query_str["filter"] = {"terms": {"metadata.document_id": document_ids_filter}} results = self._client.search(index=self._collection_name, query=query_str, size=kwargs.get("top_k", 4)) docs = [] for hit in results["hits"]["hits"]: diff --git a/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py b/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py index be4384341b..d3f5283034 100644 --- a/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py +++ b/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py @@ -171,7 +171,7 @@ class LindormVectorStore(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") filters = [] if document_ids_filter: - filters.append({"terms": {"metadata.doc_id": document_ids_filter}}) + filters.append({"terms": {"metadata.document_id": document_ids_filter}}) query = default_vector_search_query(query_vector=query_vector, k=top_k, filters=filters, **kwargs) try: @@ -214,7 +214,7 @@ class LindormVectorStore(BaseVector): filters = kwargs.get("filter", []) document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - filters.append({"terms": {"metadata.doc_id": document_ids_filter}}) + filters.append({"terms": {"metadata.document_id": document_ids_filter}}) routing = self._routing full_text_query = default_text_search_query( query_text=query, diff --git a/api/core/rag/datasource/vdb/milvus/milvus_vector.py b/api/core/rag/datasource/vdb/milvus/milvus_vector.py index 479f0fa279..e1c7416d0d 100644 --- a/api/core/rag/datasource/vdb/milvus/milvus_vector.py +++ b/api/core/rag/datasource/vdb/milvus/milvus_vector.py @@ -221,8 +221,8 @@ class MilvusVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") filter = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - filter = f'metadata["doc_id"] in ({doc_ids})' + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + filter = f'metadata["document_id"] in ({document_ids})' results = self._client.search( collection_name=self._collection_name, data=[query_vector], @@ -248,8 +248,8 @@ class MilvusVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") filter = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - filter = f'metadata["doc_id"] in ({doc_ids})' + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + filter = f'metadata["document_id"] in ({document_ids})' results = self._client.search( collection_name=self._collection_name, diff --git a/api/core/rag/datasource/vdb/myscale/myscale_vector.py b/api/core/rag/datasource/vdb/myscale/myscale_vector.py index bb4bed4f40..0a44c28bb6 100644 --- a/api/core/rag/datasource/vdb/myscale/myscale_vector.py +++ b/api/core/rag/datasource/vdb/myscale/myscale_vector.py @@ -133,8 +133,8 @@ class MyScaleVector(BaseVector): ) document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_str = f"{where_str} AND metadata['doc_id'] in ({doc_ids})" + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_str = f"{where_str} AND metadata['document_id'] in ({document_ids})" sql = f""" SELECT text, vector, metadata, {dist} as dist FROM {self._config.database}.{self._collection_name} {where_str} ORDER BY dist {order.value} LIMIT {top_k} diff --git a/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py b/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py index 055eff252c..8ff97f2f26 100644 --- a/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py +++ b/api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py @@ -157,8 +157,8 @@ class OceanBaseVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") where_clause = None if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause = f"metadata->>'$.doc_id' in ({doc_ids})" + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause = f"metadata->>'$.document_id' in ({document_ids})" ef_search = kwargs.get("ef_search", self._hnsw_ef_search) if ef_search != self._hnsw_ef_search: self._client.set_ob_hnsw_ef_search(ef_search) diff --git a/api/core/rag/datasource/vdb/opensearch/opensearch_vector.py b/api/core/rag/datasource/vdb/opensearch/opensearch_vector.py index 7fe8d126af..6636646cff 100644 --- a/api/core/rag/datasource/vdb/opensearch/opensearch_vector.py +++ b/api/core/rag/datasource/vdb/opensearch/opensearch_vector.py @@ -156,7 +156,7 @@ class OpenSearchVector(BaseVector): } document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - query["query"] = {"terms": {"metadata.doc_id": document_ids_filter}} + query["query"] = {"terms": {"metadata.document_id": document_ids_filter}} try: response = self._client.search(index=self._collection_name.lower(), body=query) @@ -184,7 +184,7 @@ class OpenSearchVector(BaseVector): full_text_query = {"query": {"match": {Field.CONTENT_KEY.value: query}}} document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - full_text_query["query"]["terms"] = {"metadata.doc_id": document_ids_filter} + full_text_query["query"]["terms"] = {"metadata.document_id": document_ids_filter} response = self._client.search(index=self._collection_name.lower(), body=full_text_query) diff --git a/api/core/rag/datasource/vdb/oracle/oraclevector.py b/api/core/rag/datasource/vdb/oracle/oraclevector.py index e7ffa38668..c525cb5a11 100644 --- a/api/core/rag/datasource/vdb/oracle/oraclevector.py +++ b/api/core/rag/datasource/vdb/oracle/oraclevector.py @@ -188,8 +188,8 @@ class OracleVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") where_clause = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause = f"WHERE metadata->>'doc_id' in ({doc_ids})" + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause = f"WHERE metadata->>'document_id' in ({document_ids})" with self._get_cursor() as cur: cur.execute( f"SELECT meta, text, vector_distance(embedding,:1) AS distance FROM {self.table_name}" @@ -249,8 +249,8 @@ class OracleVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") where_clause = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause = f" AND metadata->>'doc_id' in ({doc_ids}) " + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause = f" AND metadata->>'document_id' in ({document_ids}) " cur.execute( f"select meta, text, embedding FROM {self.table_name}" f"WHERE CONTAINS(text, :1, 1) > 0 {where_clause} " diff --git a/api/core/rag/datasource/vdb/pgvecto_rs/pgvecto_rs.py b/api/core/rag/datasource/vdb/pgvecto_rs/pgvecto_rs.py index 2e520a9efb..46aefef11d 100644 --- a/api/core/rag/datasource/vdb/pgvecto_rs/pgvecto_rs.py +++ b/api/core/rag/datasource/vdb/pgvecto_rs/pgvecto_rs.py @@ -191,7 +191,7 @@ class PGVectoRS(BaseVector): ) document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - stmt = stmt.where(self._table.meta["doc_id"].in_(document_ids_filter)) + stmt = stmt.where(self._table.meta["document_id"].in_(document_ids_filter)) res = session.execute(stmt) results = [(row[0], row[1]) for row in res] diff --git a/api/core/rag/datasource/vdb/pgvector/pgvector.py b/api/core/rag/datasource/vdb/pgvector/pgvector.py index c51e800862..1bd7a16ba4 100644 --- a/api/core/rag/datasource/vdb/pgvector/pgvector.py +++ b/api/core/rag/datasource/vdb/pgvector/pgvector.py @@ -158,8 +158,8 @@ class PGVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") where_clause = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause = f" WHERE metadata->>'doc_id' in ({doc_ids}) " + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause = f" WHERE metadata->>'document_id' in ({document_ids}) " with self._get_cursor() as cur: cur.execute( @@ -185,8 +185,8 @@ class PGVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") where_clause = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause = f" AND metadata->>'doc_id' in ({doc_ids}) " + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause = f" AND metadata->>'document_id' in ({document_ids}) " cur.execute( f"""SELECT meta, text, ts_rank(to_tsvector(coalesce(text, '')), plainto_tsquery(%s)) AS score FROM {self.table_name} diff --git a/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py b/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py index 9a9e110b6c..0ff6b3210d 100644 --- a/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py +++ b/api/core/rag/datasource/vdb/qdrant/qdrant_vector.py @@ -334,7 +334,7 @@ class QdrantVector(BaseVector): if document_ids_filter: filter.must.append( models.FieldCondition( - key="metadata.doc_id", + key="metadata.document_id", match=models.MatchAny(any=document_ids_filter), ) ) @@ -388,7 +388,7 @@ class QdrantVector(BaseVector): if document_ids_filter: scroll_filter.must.append( models.FieldCondition( - key="metadata.doc_id", + key="metadata.document_id", match=models.MatchAny(any=document_ids_filter), ) ) diff --git a/api/core/rag/datasource/vdb/relyt/relyt_vector.py b/api/core/rag/datasource/vdb/relyt/relyt_vector.py index 1643abdc71..a6c4baf4f8 100644 --- a/api/core/rag/datasource/vdb/relyt/relyt_vector.py +++ b/api/core/rag/datasource/vdb/relyt/relyt_vector.py @@ -226,7 +226,7 @@ class RelytVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") filter = kwargs.get("filter", {}) if document_ids_filter: - filter["doc_id"] = document_ids_filter + filter["document_id"] = document_ids_filter results = self.similarity_search_with_score_by_vector( k=int(kwargs.get("top_k", 4)), embedding=query_vector, filter=filter ) diff --git a/api/core/rag/datasource/vdb/tencent/tencent_vector.py b/api/core/rag/datasource/vdb/tencent/tencent_vector.py index b08dd50fe8..304d9538a7 100644 --- a/api/core/rag/datasource/vdb/tencent/tencent_vector.py +++ b/api/core/rag/datasource/vdb/tencent/tencent_vector.py @@ -151,7 +151,7 @@ class TencentVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") filter = None if document_ids_filter: - filter = Filter(Filter.In("metadata.doc_id", document_ids_filter)) + filter = Filter(Filter.In("metadata.document_id", document_ids_filter)) res = self._db.collection(self._collection_name).search( vectors=[query_vector], filter=filter, diff --git a/api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py b/api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py index f46ce2b1c7..9fcbc2ecbc 100644 --- a/api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py +++ b/api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py @@ -330,7 +330,7 @@ class TidbOnQdrantVector(BaseVector): if document_ids_filter: filter.must.append( models.FieldCondition( - key="metadata.doc_id", + key="metadata.document_id", match=models.MatchAny(any=document_ids_filter), ) ) @@ -380,7 +380,7 @@ class TidbOnQdrantVector(BaseVector): if document_ids_filter: scroll_filter.must.append( models.FieldCondition( - key="metadata.doc_id", + key="metadata.document_id", match=models.MatchAny(any=document_ids_filter), ) ) diff --git a/api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py b/api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py index e54de902d8..77c5786042 100644 --- a/api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py +++ b/api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py @@ -199,8 +199,8 @@ class TiDBVector(BaseVector): document_ids_filter = kwargs.get("document_ids_filter") where_clause = "" if document_ids_filter: - doc_ids = ", ".join(f"'{id}'" for id in document_ids_filter) - where_clause = f" WHERE meta->>'$.doc_id' in ({doc_ids}) " + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + where_clause = f" WHERE meta->>'$.document_id' in ({document_ids}) " with Session(self._engine) as session: select_statement = sql_text(f""" diff --git a/api/core/rag/datasource/vdb/upstash/upstash_vector.py b/api/core/rag/datasource/vdb/upstash/upstash_vector.py index 0a4bef9f5a..e4f15be2b0 100644 --- a/api/core/rag/datasource/vdb/upstash/upstash_vector.py +++ b/api/core/rag/datasource/vdb/upstash/upstash_vector.py @@ -90,7 +90,8 @@ class UpstashVector(BaseVector): top_k = kwargs.get("top_k", 4) document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - filter = f"doc_id in ({', '.join(f"'{id}'" for id in document_ids_filter)})" + document_ids = ", ".join(f"'{id}'" for id in document_ids_filter) + filter = f"document_id in ({document_ids})" else: filter = "" result = self.index.query( diff --git a/api/core/rag/datasource/vdb/vikingdb/vikingdb_vector.py b/api/core/rag/datasource/vdb/vikingdb/vikingdb_vector.py index 7f4c32b9c4..9166d35bc8 100644 --- a/api/core/rag/datasource/vdb/vikingdb/vikingdb_vector.py +++ b/api/core/rag/datasource/vdb/vikingdb/vikingdb_vector.py @@ -180,7 +180,7 @@ class VikingDBVector(BaseVector): docs = self._get_search_res(results, score_threshold) document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - docs = [doc for doc in docs if doc.metadata.get("doc_id") in document_ids_filter] + docs = [doc for doc in docs if doc.metadata.get("document_id") in document_ids_filter] return docs def _get_search_res(self, results, score_threshold) -> list[Document]: diff --git a/api/core/rag/datasource/vdb/weaviate/weaviate_vector.py b/api/core/rag/datasource/vdb/weaviate/weaviate_vector.py index 7038e431d6..753f3987a9 100644 --- a/api/core/rag/datasource/vdb/weaviate/weaviate_vector.py +++ b/api/core/rag/datasource/vdb/weaviate/weaviate_vector.py @@ -189,7 +189,7 @@ class WeaviateVector(BaseVector): vector = {"vector": query_vector} document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - where_filter = {"operator": "ContainsAny", "path": ["doc_id"], "valueTextArray": document_ids_filter} + where_filter = {"operator": "ContainsAny", "path": ["document_id"], "valueTextArray": document_ids_filter} query_obj = query_obj.with_where(where_filter) result = ( query_obj.with_near_vector(vector) @@ -237,7 +237,7 @@ class WeaviateVector(BaseVector): query_obj = self._client.query.get(collection_name, properties) document_ids_filter = kwargs.get("document_ids_filter") if document_ids_filter: - where_filter = {"operator": "ContainsAny", "path": ["doc_id"], "valueTextArray": document_ids_filter} + where_filter = {"operator": "ContainsAny", "path": ["document_id"], "valueTextArray": document_ids_filter} query_obj = query_obj.with_where(where_filter) query_obj = query_obj.with_additional(["vector"]) properties = ["text"]