langchain-postgres 0.0.16__tar.gz → 0.0.18__tar.gz

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/.github/workflows/_lint.yml

@@ -12,6 +12,9 @@ on:
         type: string
         description: "Python version to use"
 
+permissions:
+  contents: read
+
 env:
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/.github/workflows/_release.yml

@@ -22,6 +22,9 @@ on:
         default: false
         description: "Release from a non-main branch (danger!)"
 
+permissions:
+  contents: read
+
 env:
   PYTHON_VERSION: "3.11"
   UV_FROZEN: "true"

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/.github/workflows/_test.yml

@@ -8,6 +8,9 @@ on:
         type: string
         description: "From which folder this pipeline executes"
 
+permissions:
+  contents: read
+
 env:
   UV_FROZEN: "true"
   UV_NO_SYNC: "true"

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/.github/workflows/ci.yml

@@ -13,6 +13,9 @@ on:
 # There's no point in testing an outdated version of the code. GitHub only allows
 # a limited number of job runners to be active at the same time, so it's better to cancel
 # pointless jobs early so that more useful jobs can run sooner.
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/DEVELOPMENT.md

@@ -13,7 +13,7 @@ source .venv/bin/activate
 
 Install package in editable mode.
 ```shell
-poetry install --with dev,test,lint
+uv sync --group test
 ```
 
 Start PostgreSQL/PGVector.
@@ -28,5 +28,6 @@ docker run --rm -it --name pgvector-container \
 
 Invoke test cases.
 ```shell
+export POSTGRES_PORT=6024
 pytest -vvv
 ```

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/PKG-INFO

@@ -1,12 +1,12 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: langchain-postgres
-Version: 0.0.16
+Version: 0.0.18
 Summary: An integration package connecting Postgres and LangChain
 License-Expression: MIT
 License-File: LICENSE
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Requires-Dist: asyncpg>=0.30.0
-Requires-Dist: langchain-core<2.0,>=0.2.13
+Requires-Dist: langchain-core<2.0,>=1.2.11
 Requires-Dist: numpy<3,>=1.21
 Requires-Dist: pgvector<0.4,>=0.2.5
 Requires-Dist: psycopg-pool<4,>=3.2.1
@@ -51,6 +51,9 @@ pip install -U langchain-postgres
 * [Quickstart](https://github.com/langchain-ai/langchain-postgres/blob/main/examples/pg_vectorstore.ipynb)
 * [How-to](https://github.com/langchain-ai/langchain-postgres/blob/main/examples/pg_vectorstore_how_to.ipynb)
 
+> [!TIP]
+> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).
+
 ### Example
 
 ```python
@@ -59,7 +62,7 @@ from langchain_core.embeddings import DeterministicFakeEmbedding
 from langchain_postgres import PGEngine, PGVectorStore
 
 # Replace the connection string with your own Postgres connection string
-CONNECTION_STRING = "postgresql+psycopg3://langchain:langchain@localhost:6024/langchain"
+CONNECTION_STRING = "postgresql+psycopg://langchain:langchain@localhost:6024/langchain"
 engine = PGEngine.from_connection_string(url=CONNECTION_STRING)
 
 # Replace the vector size with your own vector size

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/README.md

@@ -35,6 +35,9 @@ pip install -U langchain-postgres
 * [Quickstart](https://github.com/langchain-ai/langchain-postgres/blob/main/examples/pg_vectorstore.ipynb)
 * [How-to](https://github.com/langchain-ai/langchain-postgres/blob/main/examples/pg_vectorstore_how_to.ipynb)
 
+> [!TIP]
+> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).
+
 ### Example
 
 ```python
@@ -43,7 +46,7 @@ from langchain_core.embeddings import DeterministicFakeEmbedding
 from langchain_postgres import PGEngine, PGVectorStore
 
 # Replace the connection string with your own Postgres connection string
-CONNECTION_STRING = "postgresql+psycopg3://langchain:langchain@localhost:6024/langchain"
+CONNECTION_STRING = "postgresql+psycopg://langchain:langchain@localhost:6024/langchain"
 engine = PGEngine.from_connection_string(url=CONNECTION_STRING)
 
 # Replace the vector size with your own vector size

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/examples/pg_vectorstore.ipynb

@@ -258,22 +258,22 @@
     "\n",
     "docs = [\n",
     "    Document(\n",
-    "        id=uuid.uuid4(),\n",
+    "        id=str(uuid.uuid4()),\n",
     "        page_content=\"there are cats in the pond\",\n",
     "        metadata={\"likes\": 1, \"location\": \"pond\", \"topic\": \"animals\"},\n",
     "    ),\n",
     "    Document(\n",
-    "        id=uuid.uuid4(),\n",
+    "        id=str(uuid.uuid4()),\n",
     "        page_content=\"ducks are also found in the pond\",\n",
     "        metadata={\"likes\": 30, \"location\": \"pond\", \"topic\": \"animals\"},\n",
     "    ),\n",
     "    Document(\n",
-    "        id=uuid.uuid4(),\n",
+    "        id=str(uuid.uuid4()),\n",
     "        page_content=\"fresh apples are available at the market\",\n",
     "        metadata={\"likes\": 20, \"location\": \"market\", \"topic\": \"food\"},\n",
     "    ),\n",
     "    Document(\n",
-    "        id=uuid.uuid4(),\n",
+    "        id=str(uuid.uuid4()),\n",
     "        page_content=\"the market also sells fresh oranges\",\n",
     "        metadata={\"likes\": 5, \"location\": \"market\", \"topic\": \"food\"},\n",
     "    ),\n",
@@ -283,6 +283,30 @@
     "await vectorstore.aadd_documents(documents=docs)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get collection\n",
+    "\n",
+    "Get collection from the vectorstore using filters and parameters."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "documents_with_apple = await vectorstore.aget(\n",
+    "    where_document={\"$ilike\": \"%apple%\"}, include=\"documents\"\n",
+    ")\n",
+    "paginated_ids = await vectorstore.aget(limit=3, offset=3)\n",
+    "\n",
+    "print(documents_with_apple[\"documents\"])\n",
+    "print(paginated_ids[\"ids\"])"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -359,7 +383,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "To enable search with filters, it is necessary to declare the columns that you want to filter on when creating the table. The vectorstore supports a set of filters that can be applied against the metadata fields of the documents.\n",
+    "To achieve performant search with filters, it is crucial to declare the columns you want to filter on within the `metadata_columns` when creating the table, as filtering directly on these columns is far more efficient than attempting to filter on fields within a metadata JSON column. The vectorstore supports a set of filters that can be applied against the metadata fields of the documents.\n",
     "\n",
     "`PGVectorStore` currently supports the following operators.\n",
     "\n",

{langchain_postgres-0.0.16 → langchain_postgres-0.0.18}/examples/pg_vectorstore_how_to.ipynb

@@ -73,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "irl7eMFnSPZr",
    "metadata": {
     "id": "irl7eMFnSPZr"
@@ -117,7 +117,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -131,7 +131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -151,7 +151,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -178,7 +178,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {
     "id": "avlyHEMn6gzU"
    },
@@ -219,7 +219,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
@@ -247,7 +247,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {
     "id": "z-AZyzAQ7bsf"
    },
@@ -327,13 +327,39 @@
     "await store.aadd_texts(all_texts, metadatas=metadatas, ids=ids)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Get collection\n",
+    "\n",
+    "Get collection from the vectorstore using filters and parameters."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "documents_with_apple = await store.aget(\n",
+    "    where_document={\"$ilike\": \"%apple%\"}, include=\"documents\"\n",
+    ")\n",
+    "paginated_ids = await store.aget(limit=3, offset=3)\n",
+    "\n",
+    "print(documents_with_apple[\"documents\"])\n",
+    "print(paginated_ids[\"ids\"])"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "### Delete documents\n",
     "\n",
-    "Documents can be deleted using ids."
+    "Documents can be deleted using IDs or metadata filters.\n",
+    "\n",
+    "#### Delete by IDs"
    ]
   },
   {
@@ -345,6 +371,47 @@
     "await store.adelete([ids[1]])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Delete by metadata filter\n",
+    "\n",
+    "You can delete documents based on metadata filters. This is useful for bulk deletion operations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Delete all documents with a specific metadata value\n",
+    "await store.adelete(filter={\"source\": \"documentation\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Delete documents matching complex filter criteria\n",
+    "await store.adelete(\n",
+    "    filter={\"$and\": [{\"category\": \"obsolete\"}, {\"year\": {\"$lt\": 2020}}]}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Delete by both IDs and filter (must match both criteria)\n",
+    "await store.adelete(ids=[\"id1\", \"id2\"], filter={\"status\": \"archived\"})"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -496,7 +563,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -530,7 +597,7 @@
    "source": [
     "### Search for documents with metadata filter\n",
     "\n",
-    "A Vector Store can take advantage of relational data to filter similarity searches. The vectorstore supports a set of filters that can be applied against the metadata fields of the documents. See the [migration guide](https://github.com/langchain-ai/langchain-postgres/blob/main/examples/migrate_pgvector_to_pgvectorstore.ipynb) for details on how to migrate to use metadata columns.\n",
+    "A Vector Store can take advantage of relational data to filter similarity searches. The vectorstore supports a set of filters that can be applied against the metadata fields of the documents. See the [migration guide](https://github.com/langchain-ai/langchain-postgres/blob/main/examples/migrate_pgvector_to_pgvectorstore.ipynb) for details on how to migrate to use metadata columns for efficient filtering.\n",
     "\n",
     "`PGVectorStore` currently supports the following operators and all Postgres data types.\n",
     "\n",
@@ -645,7 +712,7 @@
     "\n",
     "- **`metadata_columns=[\"name\", \"category\", \"price_usd\", \"quantity\", \"sku\", \"image_url\"]`**: These columns are treated as metadata for each product. Metadata provides additional information about a product, such as its name, category, price, quantity available, SKU (Stock Keeping Unit), and an image URL. This information is useful for displaying product details in search results or for filtering and categorization.\n",
     "\n",
-    "- **`metadata_json_column=\"metadata\"`**: The `metadata` column can store any additional information about the products in a flexible JSON format. This allows for storing varied and complex data that doesn't fit into the standard columns.\n"
+    "- **`metadata_json_column=\"metadata\"`**: The `metadata` column can store any additional information about the products in a flexible JSON format. This allows for storing varied and complex data that doesn't fit into the standard columns. Note that filtering on fields within the JSON but not in `metadata_columns` will be less efficient.\n"
    ]
   },
   {
@@ -959,6 +1026,13 @@
    "source": [
     "await pg_engine.adrop_table(TABLE_NAME)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -967,7 +1041,8 @@
    "toc_visible": true
   },
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": ".venv",
+   "language": "python",
    "name": "python3"
   },
   "language_info": {
@@ -980,7 +1055,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.8"
+   "version": "3.12.11"
   }
  },
  "nbformat": 4,