Update documentation (#22)

Update documentation

Author: eyurtsev

examples/vectorstore.ipynb

@@ -14,28 +14,20 @@
     "You can run the following command to spin up a pg-vector container:\n",
     "\n",
     "```shell\n",
-    "docker run --name pgvector-container -e POSTGRES_PASSWORD=langchain -d pgvector/pgvector:pg16\n",
+    "docker run --name pgvector-container -e POSTGRES_USER=langchain -e POSTGRES_PASSWORD=langchain -e POSTGRES_DB=langchain -p 6024:5432 -d pgvector/pgvector:pg16\n",
     "```\n",
     "\n",
-    "**BETA**  This vectorstore is in **beta** and **not** recommended for production usage at enterprise level.\n",
+    "## Status\n",
     "\n",
-    "The main issue with the existing implementation is:\n",
+    "This code has been ported over from langchain_community. The following changes have been made:\n",
     "\n",
-    "1) Handling of connection objects\n",
-    "2) Lack of support for schema migrations\n",
-    "\n",
-    "If you're OK with these limitations (and know how to create migrations for the table) or are fine re-creating the collection and embeddings if the schema changes, then feel free to use this implementation.\n",
-    "\n",
-    "While this code has been ported over from langchain_community with minimal changes to allow users to easily transition from langchain_community to langchain_postgres,\n",
-    "some changes still had to be made to make it easier for users that are relying on this implementation to transition to `langchain_postgres`.\n",
-    "\n",
-    "Some changes had to be made to address issues with the community implementation:\n",
-    "\n",
-    "* langchain_postgres now works with psycopg3. Please update your connnecion strings from `postgresql+psycopg2://...` to `postgresql+psycopg://langchain:langchain@...` (yes, it's the driver name is `psycopg` not `psycopg3`, but it'll use `psycopg3`.\n",
+    "* langchain_postgres works only with psycopg3. Please update your connnecion strings from `postgresql+psycopg2://...` to `postgresql+psycopg://langchain:langchain@...` (yes, it's the driver name is `psycopg` not `psycopg3`, but it'll use `psycopg3`.\n",
     "* The schema of the embedding store and collection have been changed to make add_documents work correctly with user specified ids.\n",
+    "* One has to pass an explicit connection object now.\n",
     "\n",
     "\n",
-    "This vectorstore is in **beta** and **not** recommended for production usage at enetprise level. It should be fine to use it for smaller datasets and/or for prototyping RAG."
+    "Currently, there is **no mechanism** that supports easy data migration on schema changes. So any schema changes in the vectorstore will require the user to recreate the tables and re-add the documents.\n",
+    "If this is a concern, please use a different vectorstore. If not, this implementation should be fine for your use case."
    ]
   },
   {
@@ -48,7 +40,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 1,
    "id": "42d42297-11b8-44e3-bf21-7c3d1bce8277",
    "metadata": {
     "tags": []
@@ -68,7 +60,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 2,
    "id": "979a65bd-742f-4b0d-be1e-c0baae245ec6",
    "metadata": {
     "tags": []
@@ -80,30 +72,19 @@
     "from langchain_postgres.vectorstores import PGVector\n",
     "from langchain_core.documents import Document\n",
     "\n",
-    "connection_string = \"postgresql+psycopg://langchain:langchain@localhost:6024/langchain\"\n",
+    "# See docker command above to launch a postgres instance with pgvector enabled.\n",
+    "connection = \"postgresql+psycopg://langchain:langchain@localhost:6024/langchain\" \n",
     "collection_name = \"my_docs\"\n",
     "embeddings = CohereEmbeddings()\n",
     "\n",
     "vectorstore = PGVector(\n",
-    "    embedding_function=embeddings,\n",
+    "    embeddings=embeddings,\n",
     "    collection_name=collection_name,\n",
-    "    connection_string=connection_string,\n",
+    "    connection=connection,\n",
     "    use_jsonb=True,\n",
     ")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "42211476-f875-42e1-8a7c-75805d48c717",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "vectorstore.create_tables_if_not_exists()"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "0fc32168-5a82-4629-a78d-158fe2615086",
@@ -138,7 +119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 5,
    "id": "88a288cc-ffd4-4800-b011-750c72b9fd10",
    "metadata": {
     "tags": []
@@ -161,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 6,
    "id": "73aa9124-9d49-4e10-8ed3-82255e7a4106",
    "metadata": {
     "tags": []
@@ -173,7 +154,7 @@
        "[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -184,7 +165,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 7,
    "id": "a5b2b71f-49eb-407d-b03a-dea4c0a517d6",
    "metadata": {
     "tags": []
@@ -205,7 +186,7 @@
        " Document(page_content='a new coffee shop opened on Main Street', metadata={'id': 7, 'topic': 'food', 'location': 'Main Street'})]"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -224,7 +205,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 8,
    "id": "13c69357-aaee-4de0-bcc2-7ab4419c920e",
    "metadata": {
     "tags": []
@@ -273,7 +254,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 9,
    "id": "f15a2359-6dc3-4099-8214-785f167a9ca4",
    "metadata": {
     "tags": []
@@ -288,7 +269,7 @@
        " Document(page_content='ducks are also found in the pond', metadata={'id': 2, 'topic': 'animals', 'location': 'pond'})]"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -309,7 +290,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 10,
    "id": "88f919e4-e4b0-4b5f-99b3-24c675c26d33",
    "metadata": {
     "tags": []
@@ -322,7 +303,7 @@
        " Document(page_content='there are cats in the pond', metadata={'id': 1, 'topic': 'animals', 'location': 'pond'})]"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -336,7 +317,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 11,
    "id": "88f423a4-6575-4fb8-9be2-a3da01106591",
    "metadata": {
     "tags": []
@@ -349,7 +330,7 @@
        " Document(page_content='there are cats in the pond', metadata={'id': 1, 'topic': 'animals', 'location': 'pond'})]"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -366,7 +347,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 12,
    "id": "65133340-2acd-4957-849e-029b6b5d60f0",
    "metadata": {
     "tags": []
@@ -385,7 +366,7 @@
        " Document(page_content='fresh apples are available at the market', metadata={'id': 3, 'topic': 'food', 'location': 'market'})]"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }

langchain_postgres/vectorstores.py

@@ -972,12 +972,7 @@ def from_texts(
         use_jsonb: bool = True,
         **kwargs: Any,
     ) -> PGVector:
-        """
-        Return VectorStore initialized from texts and embeddings.
-        Postgres connection string is required
-        "Either pass it as a parameter
-        or set the PGVECTOR_CONNECTION_STRING environment variable.
-        """
+        """Return VectorStore initialized from documents and embeddings."""
         embeddings = embedding.embed_documents(list(texts))
 
         return cls.__from(
@@ -1106,12 +1101,7 @@ def from_documents(
         use_jsonb: bool = True,
         **kwargs: Any,
     ) -> PGVector:
-        """
-        Return VectorStore initialized from documents and embeddings.
-        Postgres connection string is required
-        "Either pass it as a parameter
-        or set the PGVECTOR_CONNECTION_STRING environment variable.
-        """
+        """Return VectorStore initialized from documents and embeddings."""
 
         texts = [d.page_content for d in documents]
         metadatas = [d.metadata for d in documents]