pgvector-haystack 1.3.0__py3-none-any.whl → 3.0.0__py3-none-any.whl

haystack_integrations/document_stores/pgvector/document_store.py

@@ -1,10 +1,9 @@
 # SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
-import logging
 from typing import Any, Dict, List, Literal, Optional
 
-from haystack import default_from_dict, default_to_dict
+from haystack import default_from_dict, default_to_dict, logging
 from haystack.dataclasses.document import ByteStream, Document
 from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
 from haystack.document_stores.types import DuplicatePolicy
@@ -28,7 +27,6 @@ CREATE TABLE IF NOT EXISTS {schema_name}.{table_name} (
 id VARCHAR(128) PRIMARY KEY,
 embedding VECTOR({embedding_dimension}),
 content TEXT,
-dataframe JSONB,
 blob_data BYTEA,
 blob_meta JSONB,
 blob_mime_type VARCHAR(255),
@@ -37,15 +35,14 @@ meta JSONB)
 
 INSERT_STATEMENT = """
 INSERT INTO {schema_name}.{table_name}
-(id, embedding, content, dataframe, blob_data, blob_meta, blob_mime_type, meta)
-VALUES (%(id)s, %(embedding)s, %(content)s, %(dataframe)s, %(blob_data)s, %(blob_meta)s, %(blob_mime_type)s, %(meta)s)
+(id, embedding, content, blob_data, blob_meta, blob_mime_type, meta)
+VALUES (%(id)s, %(embedding)s, %(content)s, %(blob_data)s, %(blob_meta)s, %(blob_mime_type)s, %(meta)s)
 """
 
 UPDATE_STATEMENT = """
 ON CONFLICT (id) DO UPDATE SET
 embedding = EXCLUDED.embedding,
 content = EXCLUDED.content,
-dataframe = EXCLUDED.dataframe,
 blob_data = EXCLUDED.blob_data,
 blob_meta = EXCLUDED.blob_meta,
 blob_mime_type = EXCLUDED.blob_mime_type,
@@ -195,7 +192,7 @@ class PgvectorDocumentStore:
             try:
                 self._connection.close()
             except Error as e:
-                logger.debug("Failed to close connection: %s", str(e))
+                logger.debug("Failed to close connection: {e}", e=str(e))
 
         conn_str = self.connection_string.resolve_value() or ""
         connection = connect(conn_str)
@@ -297,7 +294,7 @@ class PgvectorDocumentStore:
         cursor = cursor or self.cursor
 
         sql_query_str = sql_query.as_string(cursor) if not isinstance(sql_query, str) else sql_query
-        logger.debug("SQL query: %s\nParameters: %s", sql_query_str, params)
+        logger.debug("SQL query: {query}\nParameters: {parameters}", query=sql_query_str, parameters=params)
 
         try:
             result = cursor.execute(sql_query, params)
@@ -514,7 +511,7 @@ class PgvectorDocumentStore:
         sql_insert += SQL(" RETURNING id")
 
         sql_query_str = sql_insert.as_string(self.cursor) if not isinstance(sql_insert, str) else sql_insert
-        logger.debug("SQL query: %s\nParameters: %s", sql_query_str, db_documents)
+        logger.debug("SQL query: {query}\nParameters: {parameters}", query=sql_query_str, parameters=db_documents)
 
         try:
             self.cursor.executemany(sql_insert, db_documents, returning=True)
@@ -555,18 +552,16 @@ class PgvectorDocumentStore:
             db_document["blob_data"] = blob.data if blob else None
             db_document["blob_meta"] = Jsonb(blob.meta) if blob and blob.meta else None
             db_document["blob_mime_type"] = blob.mime_type if blob and blob.mime_type else None
-
-            db_document["dataframe"] = Jsonb(db_document["dataframe"]) if db_document["dataframe"] else None
             db_document["meta"] = Jsonb(db_document["meta"])
 
             if "sparse_embedding" in db_document:
                 sparse_embedding = db_document.pop("sparse_embedding", None)
                 if sparse_embedding:
                     logger.warning(
-                        "Document %s has the `sparse_embedding` field set,"
+                        "Document {doc_id} has the `sparse_embedding` field set,"
                         "but storing sparse embeddings in Pgvector is not currently supported."
                         "The `sparse_embedding` field will be ignored.",
-                        db_document["id"],
+                        doc_id=db_document["id"],
                     )
 
             db_documents.append(db_document)
@@ -586,8 +581,7 @@ class PgvectorDocumentStore:
             blob_meta = haystack_dict.pop("blob_meta")
             blob_mime_type = haystack_dict.pop("blob_mime_type")
 
-            # postgresql returns the embedding as a string
-            # so we need to convert it to a list of floats
+            # convert the embedding to a list of floats
             if document.get("embedding") is not None:
                 haystack_dict["embedding"] = document["embedding"].tolist()
 

haystack_integrations/document_stores/pgvector/filters.py

@@ -6,7 +6,6 @@ from itertools import chain
 from typing import Any, Dict, List, Literal, Tuple
 
 from haystack.errors import FilterError
-from pandas import DataFrame
 from psycopg.sql import SQL
 from psycopg.types.json import Jsonb
 
@@ -93,10 +92,6 @@ def _parse_comparison_condition(condition: Dict[str, Any]) -> Tuple[str, List[An
         raise FilterError(msg)
 
     value: Any = condition["value"]
-    if isinstance(value, DataFrame):
-        # DataFrames are stored as JSONB and we query them as such
-        value = Jsonb(value.to_json())
-        field = f"({field})::jsonb"
 
     if field.startswith("meta."):
         field = _treat_meta_field(field, value)

{pgvector_haystack-1.3.0.dist-info → pgvector_haystack-3.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pgvector-haystack
-Version: 1.3.0
+Version: 3.0.0
 Summary: An integration of pgvector (vector search extension for Postgres) with Haystack
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/pgvector/README.md
@@ -11,15 +11,14 @@ License-File: LICENSE.txt
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Python: >=3.8
-Requires-Dist: haystack-ai
+Requires-Python: >=3.9
+Requires-Dist: haystack-ai>=2.11.0
 Requires-Dist: pgvector
 Requires-Dist: psycopg[binary]
 Description-Content-Type: text/markdown

{pgvector_haystack-1.3.0.dist-info → pgvector_haystack-3.0.0.dist-info}/RECORD

@@ -2,9 +2,9 @@ haystack_integrations/components/retrievers/pgvector/__init__.py,sha256=n4q4pUAp
 haystack_integrations/components/retrievers/pgvector/embedding_retriever.py,sha256=IEIdgKy_IWgmL5Qy_Hqkwa2mq2JxnQ_JOdjm38JPxmE,7530
 haystack_integrations/components/retrievers/pgvector/keyword_retriever.py,sha256=SYHqjTkDczobYZ2qq0z8yS9p_g8aINnzwA5AN_nKdHI,5632
 haystack_integrations/document_stores/pgvector/__init__.py,sha256=Ge-7ggarfr3x8UqNdFHUuFGiu52u49sOVe3l16WEwZU,197
-haystack_integrations/document_stores/pgvector/document_store.py,sha256=Ni9Cg9sXdsVBhuTNFhtSbJMkMNYORAlYLqcKM1lR96M,31440
-haystack_integrations/document_stores/pgvector/filters.py,sha256=rBRgDFXMSElRDOtiBkkHlheDV445HVGl-ufXRYKQaXs,8716
-pgvector_haystack-1.3.0.dist-info/METADATA,sha256=QuGnYE1syuoWC_L9-yL1Ew5j6mMl03hfHUXG_6p5PRs,2226
-pgvector_haystack-1.3.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-pgvector_haystack-1.3.0.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
-pgvector_haystack-1.3.0.dist-info/RECORD,,
+haystack_integrations/document_stores/pgvector/document_store.py,sha256=bs1MCwiQgoTw8Wrad8DaRRgIQokk8_t1fLmzxdufWS4,31267
+haystack_integrations/document_stores/pgvector/filters.py,sha256=M-_wmM1iKS1QdKhnRk27N8t2W1st2YZWAwVSFUyyTtk,8508
+pgvector_haystack-3.0.0.dist-info/METADATA,sha256=1rd0uO91j_NxG5hmxXIhn7RFPYJsDgO9w7XBqKMMw-Q,2184
+pgvector_haystack-3.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pgvector_haystack-3.0.0.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
+pgvector_haystack-3.0.0.dist-info/RECORD,,