mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-17 07:26:16 +00:00
community: add sqlite-vec vectorstore (#25003)
**Description**: Adds a vector store integration with [sqlite-vec](https://alexgarcia.xyz/sqlite-vec/), the successor to sqlite-vss that is a single C file with no external dependencies. Pretty straightforward, just copy-pasted the sqlite-vss integration and made a few tweaks and added integration tests. Only question is whether all documentation should be directed away from sqlite-vss if it is defacto deprecated (cc @asg017). --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: philippe-oger <philippe.oger@adevinta.com>
This commit is contained in:
Abhi Agarwal
GitHub
@@ -16,10 +16,11 @@ pip install SQLAlchemy
|
||||
|
||||
## Vector Store
|
||||
|
||||
See a [usage example](/docs/integrations/vectorstores/sqlitevss).
|
||||
See a [usage example](/docs/integrations/vectorstores/sqlitevec).
|
||||
|
||||
```python
|
||||
from langchain_community.vectorstores import SQLiteVSS
|
||||
from langchain_community.vectorstores import SQLiteVec
|
||||
from langchain_community.vectorstores import SQLiteVSS # legacy
|
||||
```
|
||||
|
||||
## Memory
|
||||
|
||||
323
docs/docs/integrations/vectorstores/sqlitevec.ipynb
Normal file
323
docs/docs/integrations/vectorstores/sqlitevec.ipynb
Normal file
@@ -0,0 +1,323 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_label: SQLiteVec\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"# SQLite as a Vector Store with SQLiteVec\n",
|
||||
"\n",
|
||||
"This notebook covers how to get started with the SQLiteVec vector store.\n",
|
||||
"\n",
|
||||
">[SQLite-Vec](https://alexgarcia.xyz/sqlite-vec/) is an `SQLite` extension designed for vector search, emphasizing local-first operations and easy integration into applications without external servers. It is the successor to [SQLite-VSS](https://alexgarcia.xyz/sqlite-vss/) by the same author. It is written in zero-dependency C and designed to be easy to build and use.\n",
|
||||
"\n",
|
||||
"This notebook shows how to use the `SQLiteVec` vector database."
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"You'll need to install `langchain-community` with `pip install -qU langchain-community` to use this integration"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# You need to install sqlite-vec as a dependency.\n",
|
||||
"%pip install --upgrade --quiet sqlite-vec"
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Credentials\n",
|
||||
"SQLiteVec does not require any credentials to use as the vector store is a simple SQLite file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": "## Initialization"
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"jupyter": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"from langchain_community.embeddings.sentence_transformer import (\n",
|
||||
" SentenceTransformerEmbeddings,\n",
|
||||
")\n",
|
||||
"from langchain_community.vectorstores import SQLiteVec\n",
|
||||
"\n",
|
||||
"embedding_function = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
|
||||
"vector_store = SQLiteVec(\n",
|
||||
" table=\"state_union\", db_file=\"/tmp/vec.db\", embedding=embedding_function\n",
|
||||
")"
|
||||
],
|
||||
"outputs": [],
|
||||
"execution_count": null
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": "## Manage vector store"
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": "### Add items to vector store"
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "code",
|
||||
"outputs": [],
|
||||
"execution_count": null,
|
||||
"source": "vector_store.add_texts(texts=[\"Ketanji Brown Jackson is awesome\", \"foo\", \"bar\"])"
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Update items in vector store\n",
|
||||
"Not supported yet"
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Delete items from vector store\n",
|
||||
"Not supported yet"
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": "## Query vector store"
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": "### Query directly"
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "code",
|
||||
"outputs": [],
|
||||
"execution_count": null,
|
||||
"source": "data = vector_store.similarity_search(\"Ketanji Brown Jackson\", k=4)"
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"### Query by turning into retriever\n",
|
||||
"Not supported yet"
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Usage for retrieval-augmented generation\n",
|
||||
"Refer to the documentation on sqlite-vec at https://alexgarcia.xyz/sqlite-vec/ for more information on how to use it for retrieval-augmented generation."
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## API reference\n",
|
||||
"For detailed documentation of all SQLiteVec features and configurations head to the API reference:https://api.python.langchain.com/en/latest/vectorstores/langchain_community.vectorstores.sqlitevec.SQLiteVec.html"
|
||||
]
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "markdown",
|
||||
"source": "### Other examples"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-06T14:55:55.370351Z",
|
||||
"start_time": "2023-09-06T14:55:53.547755Z"
|
||||
},
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders import TextLoader\n",
|
||||
"from langchain_community.embeddings.sentence_transformer import (\n",
|
||||
" SentenceTransformerEmbeddings,\n",
|
||||
")\n",
|
||||
"from langchain_community.vectorstores import SQLiteVec\n",
|
||||
"from langchain_text_splitters import CharacterTextSplitter\n",
|
||||
"\n",
|
||||
"# load the document and split it into chunks\n",
|
||||
"loader = TextLoader(\"../../how_to/state_of_the_union.txt\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"\n",
|
||||
"# split it into chunks\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"texts = [doc.page_content for doc in docs]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# create the open-source embedding function\n",
|
||||
"embedding_function = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# load it in sqlite-vss in a table named state_union.\n",
|
||||
"# the db_file parameter is the name of the file you want\n",
|
||||
"# as your sqlite database.\n",
|
||||
"db = SQLiteVec.from_texts(\n",
|
||||
" texts=texts,\n",
|
||||
" embedding=embedding_function,\n",
|
||||
" table=\"state_union\",\n",
|
||||
" db_file=\"/tmp/vec.db\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# query it\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"data = db.similarity_search(query)\n",
|
||||
"\n",
|
||||
"# print results\n",
|
||||
"data[0].page_content"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"source": "### Example using existing SQLite connection"
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-06T14:59:22.086252Z",
|
||||
"start_time": "2023-09-06T14:59:21.693237Z"
|
||||
},
|
||||
"collapsed": false,
|
||||
"jupyter": {
|
||||
"outputs_hidden": false
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Ketanji Brown Jackson is awesome'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain_community.document_loaders import TextLoader\n",
|
||||
"from langchain_community.embeddings.sentence_transformer import (\n",
|
||||
" SentenceTransformerEmbeddings,\n",
|
||||
")\n",
|
||||
"from langchain_community.vectorstores import SQLiteVec\n",
|
||||
"from langchain_text_splitters import CharacterTextSplitter\n",
|
||||
"\n",
|
||||
"# load the document and split it into chunks\n",
|
||||
"loader = TextLoader(\"../../how_to/state_of_the_union.txt\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"\n",
|
||||
"# split it into chunks\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"texts = [doc.page_content for doc in docs]\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# create the open-source embedding function\n",
|
||||
"embedding_function = SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
|
||||
"connection = SQLiteVec.create_connection(db_file=\"/tmp/vec.db\")\n",
|
||||
"\n",
|
||||
"db1 = SQLiteVec(\n",
|
||||
" table=\"state_union\", embedding=embedding_function, connection=connection\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"db1.add_texts([\"Ketanji Brown Jackson is awesome\"])\n",
|
||||
"# query it again\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"data = db1.similarity_search(query)\n",
|
||||
"\n",
|
||||
"# print results\n",
|
||||
"data[0].page_content"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
Reference in New Issue
Block a user