pgvector-haystack 2.0.0__py3-none-any.whl → 3.0.1__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
@@ -24,7 +23,7 @@ from .filters import _convert_filters_to_where_clause_and_params
 logger = logging.getLogger(__name__)
 
 CREATE_TABLE_STATEMENT = """
-CREATE TABLE IF NOT EXISTS {schema_name}.{table_name} (
+CREATE TABLE {schema_name}.{table_name} (
 id VARCHAR(128) PRIMARY KEY,
 embedding VECTOR({embedding_dimension}),
 content TEXT,
@@ -193,7 +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)
@@ -295,7 +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)
@@ -311,13 +310,22 @@ class PgvectorDocumentStore:
         Creates the table to store Haystack documents if it doesn't exist yet.
         """
 
-        create_sql = SQL(CREATE_TABLE_STATEMENT).format(
-            schema_name=Identifier(self.schema_name),
-            table_name=Identifier(self.table_name),
-            embedding_dimension=SQLLiteral(self.embedding_dimension),
+        table_exists = bool(
+            self._execute_sql(
+                "SELECT 1 FROM pg_tables WHERE schemaname = %s AND tablename = %s",
+                (self.schema_name, self.table_name),
+                "Could not check if table exists",
+            ).fetchone()
         )
 
-        self._execute_sql(create_sql, error_msg="Could not create table in PgvectorDocumentStore")
+        if not table_exists:
+            create_sql = SQL(CREATE_TABLE_STATEMENT).format(
+                schema_name=Identifier(self.schema_name),
+                table_name=Identifier(self.table_name),
+                embedding_dimension=SQLLiteral(self.embedding_dimension),
+            )
+
+            self._execute_sql(create_sql, error_msg="Could not create table in PgvectorDocumentStore")
 
     def delete_table(self):
         """
@@ -512,7 +520,7 @@ 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)
@@ -555,24 +563,14 @@ class PgvectorDocumentStore:
             db_document["blob_mime_type"] = blob.mime_type if blob and blob.mime_type else None
             db_document["meta"] = Jsonb(db_document["meta"])
 
-            if "dataframe" in db_document:
-                dataframe = db_document.pop("dataframe", None)
-                if dataframe:
-                    logger.warning(
-                        "Document %s has the `dataframe` field set. "
-                        "PgvectorDocumentStore no longer supports dataframes and this field will be ignored. "
-                        "The `dataframe` field will soon be removed from Haystack Document.",
-                        db_document["id"],
-                    )
-
             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)
@@ -591,20 +589,11 @@ class PgvectorDocumentStore:
             blob_data = haystack_dict.pop("blob_data")
             blob_meta = haystack_dict.pop("blob_meta")
             blob_mime_type = haystack_dict.pop("blob_mime_type")
-            dataframe = haystack_dict.pop("dataframe", None)
 
             # convert the embedding to a list of floats
             if document.get("embedding") is not None:
                 haystack_dict["embedding"] = document["embedding"].tolist()
 
-            if dataframe:
-                logger.warning(
-                    "Document %s has the `dataframe` field set. "
-                    "PgvectorDocumentStore no longer supports dataframes and this field will be ignored. "
-                    "The `dataframe` field will soon be removed from Haystack Document.",
-                    haystack_dict["id"],
-                )
-
             haystack_document = Document.from_dict(haystack_dict)
 
             if blob_data:

{pgvector_haystack-2.0.0.dist-info → pgvector_haystack-3.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pgvector-haystack
-Version: 2.0.0
+Version: 3.0.1
 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-2.0.0.dist-info → pgvector_haystack-3.0.1.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=rirjSAMaPLADimwPcj-WQohrQbnXpTWgOCSIJy3qpPg,32148
+haystack_integrations/document_stores/pgvector/document_store.py,sha256=gzyJJkDdGFfi6gdpPjKpTw9Ya2dEY28p9HstSjiJbIU,31590
 haystack_integrations/document_stores/pgvector/filters.py,sha256=M-_wmM1iKS1QdKhnRk27N8t2W1st2YZWAwVSFUyyTtk,8508
-pgvector_haystack-2.0.0.dist-info/METADATA,sha256=NhUGkaP8KzfX8qrlU5LrI-pjEQ3B4UDCfqN-WvlXsGY,2226
-pgvector_haystack-2.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-pgvector_haystack-2.0.0.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
-pgvector_haystack-2.0.0.dist-info/RECORD,,
+pgvector_haystack-3.0.1.dist-info/METADATA,sha256=9xjXoMRnchq0NlQOflI_EQHdmn4fwZgwzLS7vkUVmIw,2184
+pgvector_haystack-3.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pgvector_haystack-3.0.1.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
+pgvector_haystack-3.0.1.dist-info/RECORD,,