pgvector-haystack 2.0.0__tar.gz → 3.0.0__tar.gz

{pgvector_haystack-2.0.0 → pgvector_haystack-3.0.0}/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## [integrations/pgvector-v2.0.0] - 2025-02-13
+
+### 🧹 Chores
+
+- Pgvector - remove support for dataframe (#1370)
+
 ## [integrations/pgvector-v1.3.0] - 2025-02-03
 
 ### 🚀 Features

{pgvector_haystack-2.0.0 → pgvector_haystack-3.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pgvector-haystack
-Version: 2.0.0
+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-2.0.0 → pgvector_haystack-3.0.0}/pyproject.toml

@@ -7,7 +7,7 @@ name = "pgvector-haystack"
 dynamic = ["version"]
 description = "An integration of pgvector (vector search extension for Postgres) with Haystack"
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 license = "Apache-2.0"
 keywords = []
 authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
@@ -15,7 +15,6 @@ classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.8",
   "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
@@ -23,7 +22,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai", "pgvector", "psycopg[binary]"]
+dependencies = ["haystack-ai>=2.11.0", "pgvector", "psycopg[binary]"]
 
 [project.urls]
 Source = "https://github.com/deepset-ai/haystack-core-integrations"
@@ -60,7 +59,7 @@ cov-retry = ["test-cov-retry", "cov-report"]
 docs = ["pydoc-markdown pydoc/config.yml"]
 
 [[tool.hatch.envs.all.matrix]]
-python = ["3.8", "3.9", "3.10", "3.11", "3.12"]
+python = [ "3.9", "3.10", "3.11", "3.12"]
 
 [tool.hatch.envs.lint]
 installer = "uv"

{pgvector_haystack-2.0.0 → pgvector_haystack-3.0.0}/src/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
@@ -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)
@@ -512,7 +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)
@@ -555,24 +554,14 @@ 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 +580,11 @@ 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: