x

Author: eyurtsev

examples/migrate_pgvector_to_pgvectorstore.ipynb

@@ -280,7 +280,6 @@
    "outputs": [],
    "source": [
     "from langchain_core.embeddings import FakeEmbeddings\n",
-    "\n",
     "from langchain_postgres import PGVectorStore\n",
     "from langchain_postgres.utils.pgvector_migrator import amigrate_pgvector_collection\n",
     "\n",

examples/pg_vectorstore.ipynb

@@ -136,9 +136,8 @@
    },
    "outputs": [],
    "source": [
-    "from sqlalchemy.exc import ProgrammingError\n",
-    "\n",
     "from langchain_postgres import Column\n",
+    "from sqlalchemy.exc import ProgrammingError\n",
     "\n",
     "try:\n",
     "    await pg_engine.ainit_vectorstore_table(\n",
@@ -150,7 +149,7 @@
     "            Column(\"topic\", \"TEXT\"),\n",
     "        ],\n",
     "    )\n",
-    "except ProgrammingError:\n",
+    "except ProgrammingError as e:\n",
     "    # Catching the exception here\n",
     "    print(\"Table already exists. Skipping creation.\")"
    ]
@@ -192,7 +191,7 @@
    "source": [
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
-    "embedding = OpenAIEmbeddings(model=\"text-embedding-3-small\")"
+    "embedding =  OpenAIEmbeddings(model=\"text-embedding-3-small\")"
    ]
   },
   {
@@ -227,7 +226,7 @@
     "    engine=pg_engine,\n",
     "    table_name=TABLE_NAME,\n",
     "    embedding_service=embedding,\n",
-    "    metadata_columns=[\"location\", \"topic\"],\n",
+    "    metadata_columns=[\"location\", \"topic\"]\n",
     ")"
    ]
   },
@@ -253,9 +252,9 @@
    "outputs": [],
    "source": [
     "import uuid\n",
-    "\n",
     "from langchain_core.documents import Document\n",
     "\n",
+    "\n",
     "docs = [\n",
     "    Document(\n",
     "        id=uuid.uuid4(),\n",
@@ -389,9 +388,7 @@
    },
    "outputs": [],
    "source": [
-    "await vectorstore.asimilarity_search(\n",
-    "    \"birds\", filter={\"$or\": [{\"topic\": \"animals\"}, {\"location\": \"market\"}]}\n",
-    ")"
+    "await vectorstore.asimilarity_search(\"birds\", filter={\"$or\": [{\"topic\": \"animals\"}, {\"location\": \"market\"}]})"
    ]
   },
   {
@@ -413,9 +410,7 @@
    },
    "outputs": [],
    "source": [
-    "await vectorstore.asimilarity_search(\n",
-    "    \"apple\", filter={\"topic\": {\"$in\": [\"food\", \"animals\"]}}\n",
-    ")"
+    "await vectorstore.asimilarity_search(\"apple\", filter={\"topic\": {\"$in\": [\"food\", \"animals\"]}})"
    ]
   },
   {
@@ -426,9 +421,7 @@
    },
    "outputs": [],
    "source": [
-    "await vectorstore.asimilarity_search(\n",
-    "    \"sales of fruit\", filter={\"topic\": {\"$ne\": \"animals\"}}\n",
-    ")"
+    "await vectorstore.asimilarity_search(\"sales of fruit\", filter={\"topic\": {\"$ne\": \"animals\"}})"
    ]
   },
   {
@@ -457,7 +450,7 @@
    "source": [
     "from langchain_postgres.v2.indexes import IVFFlatIndex\n",
     "\n",
-    "index = IVFFlatIndex()  # Add an index using a default index name\n",
+    "index = IVFFlatIndex() # Add an index using a default index name\n",
     "await vectorstore.aapply_vector_index(index)"
    ]
   },

examples/pg_vectorstore_how_to.ipynb

@@ -278,9 +278,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import uuid\n",
-    "\n",
     "from langchain_core.documents import Document\n",
+    "import uuid\n",
     "\n",
     "docs = [\n",
     "    Document(\n",
@@ -401,7 +400,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_postgres.v2.indexes import HNSWIndex, IVFFlatIndex\n",
+    "from langchain_postgres.v2.indexes import IVFFlatIndex, HNSWIndex\n",
     "\n",
     "index = IVFFlatIndex()\n",
     "await store.aapply_vector_index(index)\n",
@@ -462,7 +461,7 @@
    "outputs": [],
    "source": [
     "await store.adrop_vector_index()  # Delete index using the default name\n",
-    "await store.adrop_vector_index(\"my-hnsw-index\")  # Delete index using the index name"
+    "await store.adrop_vector_index(\"my-hnsw-index\") # Delete index using the index name"
    ]
   },
   {

examples/vectorstore.ipynb

@@ -68,9 +68,8 @@
    "outputs": [],
    "source": [
     "from langchain_cohere import CohereEmbeddings\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
     "from langchain_postgres.vectorstores import PGVector\n",
+    "from langchain_core.documents import Document\n",
     "\n",
     "# See docker command above to launch a postgres instance with pgvector enabled.\n",
     "connection = \"postgresql+psycopg://langchain:langchain@localhost:6024/langchain\"\n",

langchain_postgres/chat_message_histories.py

@@ -2,7 +2,6 @@
 
 This client provides support for both sync and async via psycopg 3.
 """
-
 from __future__ import annotations
 
 import json