pgvector-haystack 0.3.0__tar.gz → 0.4.0__tar.gz

pgvector_haystack-0.4.0/CHANGELOG.md

@@ -0,0 +1,35 @@
+# Changelog
+
+## [unreleased]
+
+### 🚀 Features
+
+- Defer the database connection to when it's needed (#773)
+
+## [integrations/pgvector-v0.2.0] - 2024-05-08
+
+### 🚀 Features
+
+- `MongoDBAtlasEmbeddingRetriever` (#427)
+- Implement keyword retrieval for pgvector integration (#644)
+
+### 🐛 Bug Fixes
+
+- Fix order of API docs (#447)
+
+This PR will also push the docs to Readme
+
+### 📚 Documentation
+
+- Update category slug (#442)
+- Disable-class-def (#556)
+
+## [integrations/pgvector-v0.1.0] - 2024-02-14
+
+### 🐛 Bug Fixes
+
+- Fix linting (#328)
+
+
+
+<!-- generated by git-cliff -->

{pgvector_haystack-0.3.0 → pgvector_haystack-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pgvector-haystack
-Version: 0.3.0
+Version: 0.4.0
 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

{pgvector_haystack-0.3.0 → pgvector_haystack-0.4.0}/src/haystack_integrations/document_stores/pgvector/document_store.py

@@ -69,10 +69,6 @@ VECTOR_FUNCTION_TO_POSTGRESQL_OPS = {
 
 HNSW_INDEX_CREATION_VALID_KWARGS = ["m", "ef_construction"]
 
-HNSW_INDEX_NAME = "haystack_hnsw_index"
-
-KEYWORD_INDEX_NAME = "haystack_keyword_index"
-
 
 class PgvectorDocumentStore:
     """
@@ -91,7 +87,9 @@ class PgvectorDocumentStore:
         search_strategy: Literal["exact_nearest_neighbor", "hnsw"] = "exact_nearest_neighbor",
         hnsw_recreate_index_if_exists: bool = False,
         hnsw_index_creation_kwargs: Optional[Dict[str, int]] = None,
+        hnsw_index_name: str = "haystack_hnsw_index",
         hnsw_ef_search: Optional[int] = None,
+        keyword_index_name: str = "haystack_keyword_index",
     ):
         """
         Creates a new PgvectorDocumentStore instance.
@@ -127,9 +125,11 @@ class PgvectorDocumentStore:
         :param hnsw_index_creation_kwargs: Additional keyword arguments to pass to the HNSW index creation.
             Only used if search_strategy is set to `"hnsw"`. You can find the list of valid arguments in the
             [pgvector documentation](https://github.com/pgvector/pgvector?tab=readme-ov-file#hnsw)
+        :param hnsw_index_name: Index name for the HNSW index.
         :param hnsw_ef_search: The `ef_search` parameter to use at query time. Only used if search_strategy is set to
             `"hnsw"`. You can find more information about this parameter in the
             [pgvector documentation](https://github.com/pgvector/pgvector?tab=readme-ov-file#hnsw).
+        :param keyword_index_name: Index name for the Keyword index.
         """
 
         self.connection_string = connection_string
@@ -143,7 +143,9 @@ class PgvectorDocumentStore:
         self.search_strategy = search_strategy
         self.hnsw_recreate_index_if_exists = hnsw_recreate_index_if_exists
         self.hnsw_index_creation_kwargs = hnsw_index_creation_kwargs or {}
+        self.hnsw_index_name = hnsw_index_name
         self.hnsw_ef_search = hnsw_ef_search
+        self.keyword_index_name = keyword_index_name
         self.language = language
         self._connection = None
         self._cursor = None
@@ -209,7 +211,9 @@ class PgvectorDocumentStore:
             search_strategy=self.search_strategy,
             hnsw_recreate_index_if_exists=self.hnsw_recreate_index_if_exists,
             hnsw_index_creation_kwargs=self.hnsw_index_creation_kwargs,
+            hnsw_index_name=self.hnsw_index_name,
             hnsw_ef_search=self.hnsw_ef_search,
+            keyword_index_name=self.keyword_index_name,
             language=self.language,
         )
 
@@ -281,7 +285,7 @@ class PgvectorDocumentStore:
         index_exists = bool(
             self._execute_sql(
                 "SELECT 1 FROM pg_indexes WHERE tablename = %s AND indexname = %s",
-                (self.table_name, KEYWORD_INDEX_NAME),
+                (self.table_name, self.keyword_index_name),
                 "Could not check if keyword index exists",
             ).fetchone()
         )
@@ -289,7 +293,7 @@ class PgvectorDocumentStore:
         sql_create_index = SQL(
             "CREATE INDEX {index_name} ON {table_name} USING GIN (to_tsvector({language}, content))"
         ).format(
-            index_name=Identifier(KEYWORD_INDEX_NAME),
+            index_name=Identifier(self.keyword_index_name),
             table_name=Identifier(self.table_name),
             language=SQLLiteral(self.language),
         )
@@ -312,7 +316,7 @@ class PgvectorDocumentStore:
         index_exists = bool(
             self._execute_sql(
                 "SELECT 1 FROM pg_indexes WHERE tablename = %s AND indexname = %s",
-                (self.table_name, HNSW_INDEX_NAME),
+                (self.table_name, self.hnsw_index_name),
                 "Could not check if HNSW index exists",
             ).fetchone()
         )
@@ -325,7 +329,7 @@ class PgvectorDocumentStore:
             )
             return
 
-        sql_drop_index = SQL("DROP INDEX IF EXISTS {index_name}").format(index_name=Identifier(HNSW_INDEX_NAME))
+        sql_drop_index = SQL("DROP INDEX IF EXISTS {index_name}").format(index_name=Identifier(self.hnsw_index_name))
         self._execute_sql(sql_drop_index, error_msg="Could not drop HNSW index")
 
         self._create_hnsw_index()
@@ -343,7 +347,7 @@ class PgvectorDocumentStore:
         }
 
         sql_create_index = SQL("CREATE INDEX {index_name} ON {table_name} USING hnsw (embedding {ops}) ").format(
-            index_name=Identifier(HNSW_INDEX_NAME), table_name=Identifier(self.table_name), ops=SQL(pg_ops)
+            index_name=Identifier(self.hnsw_index_name), table_name=Identifier(self.table_name), ops=SQL(pg_ops)
         )
 
         if actual_hnsw_index_creation_kwargs:

{pgvector_haystack-0.3.0 → pgvector_haystack-0.4.0}/tests/test_document_store.py

@@ -53,7 +53,9 @@ def test_init(monkeypatch):
         search_strategy="hnsw",
         hnsw_recreate_index_if_exists=True,
         hnsw_index_creation_kwargs={"m": 32, "ef_construction": 128},
+        hnsw_index_name="my_hnsw_index",
         hnsw_ef_search=50,
+        keyword_index_name="my_keyword_index",
     )
 
     assert document_store.table_name == "my_table"
@@ -63,7 +65,9 @@ def test_init(monkeypatch):
     assert document_store.search_strategy == "hnsw"
     assert document_store.hnsw_recreate_index_if_exists
     assert document_store.hnsw_index_creation_kwargs == {"m": 32, "ef_construction": 128}
+    assert document_store.hnsw_index_name == "my_hnsw_index"
     assert document_store.hnsw_ef_search == 50
+    assert document_store.keyword_index_name == "my_keyword_index"
 
 
 @pytest.mark.usefixtures("patches_for_unit_tests")
@@ -78,7 +82,9 @@ def test_to_dict(monkeypatch):
         search_strategy="hnsw",
         hnsw_recreate_index_if_exists=True,
         hnsw_index_creation_kwargs={"m": 32, "ef_construction": 128},
+        hnsw_index_name="my_hnsw_index",
         hnsw_ef_search=50,
+        keyword_index_name="my_keyword_index",
     )
 
     assert document_store.to_dict() == {
@@ -93,7 +99,9 @@ def test_to_dict(monkeypatch):
             "hnsw_recreate_index_if_exists": True,
             "language": "english",
             "hnsw_index_creation_kwargs": {"m": 32, "ef_construction": 128},
+            "hnsw_index_name": "my_hnsw_index",
             "hnsw_ef_search": 50,
+            "keyword_index_name": "my_keyword_index",
         },
     }
 

{pgvector_haystack-0.3.0 → pgvector_haystack-0.4.0}/tests/test_retrievers.py

@@ -48,7 +48,9 @@ class TestEmbeddingRetriever:
                         "hnsw_recreate_index_if_exists": False,
                         "language": "english",
                         "hnsw_index_creation_kwargs": {},
+                        "hnsw_index_name": "haystack_hnsw_index",
                         "hnsw_ef_search": None,
+                        "keyword_index_name": "haystack_keyword_index",
                     },
                 },
                 "filters": {"field": "value"},
@@ -75,7 +77,9 @@ class TestEmbeddingRetriever:
                         "search_strategy": "exact_nearest_neighbor",
                         "hnsw_recreate_index_if_exists": False,
                         "hnsw_index_creation_kwargs": {},
+                        "hnsw_index_name": "haystack_hnsw_index",
                         "hnsw_ef_search": None,
+                        "keyword_index_name": "haystack_keyword_index",
                     },
                 },
                 "filters": {"field": "value"},
@@ -96,7 +100,9 @@ class TestEmbeddingRetriever:
         assert document_store.search_strategy == "exact_nearest_neighbor"
         assert not document_store.hnsw_recreate_index_if_exists
         assert document_store.hnsw_index_creation_kwargs == {}
+        assert document_store.hnsw_index_name == "haystack_hnsw_index"
         assert document_store.hnsw_ef_search is None
+        assert document_store.keyword_index_name == "haystack_keyword_index"
 
         assert retriever.filters == {"field": "value"}
         assert retriever.top_k == 5
@@ -149,7 +155,9 @@ class TestKeywordRetriever:
                         "hnsw_recreate_index_if_exists": False,
                         "language": "english",
                         "hnsw_index_creation_kwargs": {},
+                        "hnsw_index_name": "haystack_hnsw_index",
                         "hnsw_ef_search": None,
+                        "keyword_index_name": "haystack_keyword_index",
                     },
                 },
                 "filters": {"field": "value"},
@@ -175,7 +183,9 @@ class TestKeywordRetriever:
                         "search_strategy": "exact_nearest_neighbor",
                         "hnsw_recreate_index_if_exists": False,
                         "hnsw_index_creation_kwargs": {},
+                        "hnsw_index_name": "haystack_hnsw_index",
                         "hnsw_ef_search": None,
+                        "keyword_index_name": "haystack_keyword_index",
                     },
                 },
                 "filters": {"field": "value"},
@@ -195,7 +205,9 @@ class TestKeywordRetriever:
         assert document_store.search_strategy == "exact_nearest_neighbor"
         assert not document_store.hnsw_recreate_index_if_exists
         assert document_store.hnsw_index_creation_kwargs == {}
+        assert document_store.hnsw_index_name == "haystack_hnsw_index"
         assert document_store.hnsw_ef_search is None
+        assert document_store.keyword_index_name == "haystack_keyword_index"
 
         assert retriever.filters == {"field": "value"}
         assert retriever.top_k == 5