mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 13:06:03 +00:00
Integrate Clickhouse as Vector Store (#5650)
<!-- Thank you for contributing to LangChain! Your PR will appear in our release under the title you set. Please make sure it highlights your valuable contribution. Replace this with a description of the change, the issue it fixes (if applicable), and relevant context. List any dependencies required for this change. After you're done, someone will review your PR. They may suggest improvements. If no one reviews your PR within a few days, feel free to @-mention the same people again, as notifications can get lost. Finally, we'd love to show appreciation for your contribution - if you'd like us to shout you out on Twitter, please also include your handle! --> #### Description This PR is mainly to integrate open source version of ClickHouse as Vector Store as it is easy for both local development and adoption of LangChain for enterprises who already have large scale clickhouse deployment. ClickHouse is a open source real-time OLAP database with full SQL support and a wide range of functions to assist users in writing analytical queries. Some of these functions and data structures perform distance operations between vectors, [enabling ClickHouse to be used as a vector database](https://clickhouse.com/blog/vector-search-clickhouse-p1). Recently added ClickHouse capabilities like [Approximate Nearest Neighbour (ANN) indices](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/annindexes) support faster approximate matching of vectors and provide a promising development aimed to further enhance the vector matching capabilities of ClickHouse. In LangChain, some ClickHouse based commercial variant vector stores like [Chroma](https://github.com/hwchase17/langchain/blob/master/langchain/vectorstores/chroma.py) and [MyScale](https://github.com/hwchase17/langchain/blob/master/langchain/vectorstores/myscale.py), etc are already integrated, but for some enterprises with large scale Clickhouse clusters deployment, it will be more straightforward to upgrade existing clickhouse infra instead of moving to another similar vector store solution, so we believe it's a valid requirement to integrate open source version of ClickHouse as vector store. As `clickhouse-connect` is already included by other integrations, this PR won't include any new dependencies. #### Before submitting <!-- If you're adding a new integration, please include: 1. Added a test for the integration: https://github.com/haoch/langchain/blob/clickhouse/tests/integration_tests/vectorstores/test_clickhouse.py 2. Added an example notebook and document showing its use: * Notebook: https://github.com/haoch/langchain/blob/clickhouse/docs/modules/indexes/vectorstores/examples/clickhouse.ipynb * Doc: https://github.com/haoch/langchain/blob/clickhouse/docs/integrations/clickhouse.md See contribution guidelines for more information on how to write tests, lint etc: https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md --> 1. Added a test for the integration: https://github.com/haoch/langchain/blob/clickhouse/tests/integration_tests/vectorstores/test_clickhouse.py 2. Added an example notebook and document showing its use: * Notebook: https://github.com/haoch/langchain/blob/clickhouse/docs/modules/indexes/vectorstores/examples/clickhouse.ipynb * Doc: https://github.com/haoch/langchain/blob/clickhouse/docs/integrations/clickhouse.md #### Who can review? Tag maintainers/contributors who might be interested: <!-- For a quicker response, figure out the right person to tag with @ @hwchase17 - project lead Tracing / Callbacks - @agola11 Async - @agola11 DataLoaders - @eyurtsev Models - @hwchase17 - @agola11 Agents / Tools / Toolkits - @vowelparrot VectorStores / Retrievers / Memory - @dev2049 --> @hwchase17 @dev2049 Could you please help review? --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
This commit is contained in:
Hao Chen
GitHub
52
docs/integrations/clickhouse.md
Normal file
52
docs/integrations/clickhouse.md
Normal file
@@ -0,0 +1,52 @@
|
||||
# ClickHouse
|
||||
|
||||
This page covers how to use ClickHouse Vector Search within LangChain.
|
||||
|
||||
[ClickHouse](https://clickhouse.com) is a open source real-time OLAP database with full SQL support and a wide range of functions to assist users in writing analytical queries. Some of these functions and data structures perform distance operations between vectors, enabling ClickHouse to be used as a vector database.
|
||||
|
||||
Due to the fully parallelized query pipeline, ClickHouse can process vector search operations very quickly, especially when performing exact matching through a linear scan over all rows, delivering processing speed comparable to dedicated vector databases.
|
||||
|
||||
High compression levels, tunable through custom compression codecs, enable very large datasets to be stored and queried. ClickHouse is not memory-bound, allowing multi-TB datasets containing embeddings to be queried.
|
||||
|
||||
The capabilities for computing the distance between two vectors are just another SQL function and can be effectively combined with more traditional SQL filtering and aggregation capabilities. This allows vectors to be stored and queried alongside metadata, and even rich text, enabling a broad array of use cases and applications.
|
||||
|
||||
Finally, experimental ClickHouse capabilities like [Approximate Nearest Neighbour (ANN) indices](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/annindexes) support faster approximate matching of vectors and provide a promising development aimed to further enhance the vector matching capabilities of ClickHouse.
|
||||
|
||||
## Installation
|
||||
- Install clickhouse server by [binary](https://clickhouse.com/docs/en/install) or [docker image](https://hub.docker.com/r/clickhouse/clickhouse-server/)
|
||||
- Install the Python SDK with `pip install clickhouse-connect`
|
||||
|
||||
### Configure clickhouse vector index
|
||||
|
||||
Customize `ClickhouseSettings` object with parameters
|
||||
|
||||
```python
|
||||
from langchain.vectorstores import ClickHouse, ClickhouseSettings
|
||||
config = ClickhouseSettings(host="<clickhouse-server-host>", port=8123, ...)
|
||||
index = Clickhouse(embedding_function, config)
|
||||
index.add_documents(...)
|
||||
```
|
||||
|
||||
## Wrappers
|
||||
supported functions:
|
||||
- `add_texts`
|
||||
- `add_documents`
|
||||
- `from_texts`
|
||||
- `from_documents`
|
||||
- `similarity_search`
|
||||
- `asimilarity_search`
|
||||
- `similarity_search_by_vector`
|
||||
- `asimilarity_search_by_vector`
|
||||
- `similarity_search_with_relevance_scores`
|
||||
|
||||
### VectorStore
|
||||
|
||||
There exists a wrapper around open source Clickhouse database, allowing you to use it as a vectorstore,
|
||||
whether for semantic search or similar example retrieval.
|
||||
|
||||
To import this vectorstore:
|
||||
```python
|
||||
from langchain.vectorstores import Clickhouse
|
||||
```
|
||||
|
||||
For a more detailed walkthrough of the MyScale wrapper, see [this notebook](../modules/indexes/vectorstores/examples/clickhouse.ipynb)
|
||||
399
docs/modules/indexes/vectorstores/examples/clickhouse.ipynb
Normal file
399
docs/modules/indexes/vectorstores/examples/clickhouse.ipynb
Normal file
@@ -0,0 +1,399 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "683953b3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ClickHouse Vector Search\n",
|
||||
"\n",
|
||||
"> [ClickHouse](https://clickhouse.com/) is the fastest and most resource efficient open-source database for real-time apps and analytics with full SQL support and a wide range of functions to assist users in writing analytical queries. Lately added data structures and distance search functions (like `L2Distance`) as well as [approximate nearest neighbor search indexes](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/annindexes) enable ClickHouse to be used as a high performance and scalable vector database to store and search vectors with SQL.\n",
|
||||
"\n",
|
||||
"This notebook shows how to use functionality related to the `ClickHouse` vector search."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "43ead5d5-2c1f-4dce-a69a-cb00e4f9d6f0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setting up envrionments"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b2c434bc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Setting up local clickhouse server with docker (optional)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "249a7751",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:43:43.035606Z",
|
||||
"start_time": "2023-06-03T08:43:42.618531Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"! docker run -d -p 8123:8123 -p9000:9000 --name langchain-clickhouse-server --ulimit nofile=262144:262144 clickhouse/clickhouse-server:23.4.2.11"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7bd3c1c0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Setup up clickhouse client driver"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9d614bf8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install clickhouse-connect"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "15a1d477-9cdb-4d82-b019-96951ecb2b72",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We want to use OpenAIEmbeddings so we have to get the OpenAI API Key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "91003ea5-0c8c-436c-a5de-aaeaeef2f458",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:49:35.383673Z",
|
||||
"start_time": "2023-06-03T08:49:33.984547Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"if not os.environ['OPENAI_API_KEY']:\n",
|
||||
" os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "aac9563e",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:33:31.554934Z",
|
||||
"start_time": "2023-06-03T08:33:31.549590Z"
|
||||
},
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.vectorstores import Clickhouse, ClickhouseSettings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "a3c3999a",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:33:32.527387Z",
|
||||
"start_time": "2023-06-03T08:33:32.501312Z"
|
||||
},
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"loader = TextLoader('../../../state_of_the_union.txt')\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "6e104aee",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:33:35.503823Z",
|
||||
"start_time": "2023-06-03T08:33:33.745832Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Inserting data...: 100%|██████████| 42/42 [00:00<00:00, 2801.49it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for d in docs:\n",
|
||||
" d.metadata = {'some': 'metadata'}\n",
|
||||
"settings = ClickhouseSettings(table=\"clickhouse_vector_search_example\")\n",
|
||||
"docsearch = Clickhouse.from_documents(docs, embeddings, config=settings)\n",
|
||||
"\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = docsearch.similarity_search(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "9c608226",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"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",
|
||||
"\n",
|
||||
"Tonight, 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",
|
||||
"\n",
|
||||
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
|
||||
"\n",
|
||||
"And 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.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(docs[0].page_content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e3a8b105",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Get connection info and data schema"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "69996818",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:28:58.252991Z",
|
||||
"start_time": "2023-06-03T08:28:58.197560Z"
|
||||
},
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[92m\u001b[1mdefault.clickhouse_vector_search_example @ localhost:8123\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1musername: None\u001b[0m\n",
|
||||
"\n",
|
||||
"Table Schema:\n",
|
||||
"---------------------------------------------------\n",
|
||||
"|\u001b[94mid \u001b[0m|\u001b[96mNullable(String) \u001b[0m|\n",
|
||||
"|\u001b[94mdocument \u001b[0m|\u001b[96mNullable(String) \u001b[0m|\n",
|
||||
"|\u001b[94membedding \u001b[0m|\u001b[96mArray(Float32) \u001b[0m|\n",
|
||||
"|\u001b[94mmetadata \u001b[0m|\u001b[96mObject('json') \u001b[0m|\n",
|
||||
"|\u001b[94muuid \u001b[0m|\u001b[96mUUID \u001b[0m|\n",
|
||||
"---------------------------------------------------\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(str(docsearch))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "324ac147",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Clickhouse table schema"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b5bd7c5b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"> Clickhouse table will be automatically created if not exist by default. Advanced users could pre-create the table with optimized settings. For distributed Clickhouse cluster with sharding, table engine should be configured as `Distributed`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "54f4f561",
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Clickhouse Table DDL:\n",
|
||||
"\n",
|
||||
"CREATE TABLE IF NOT EXISTS default.clickhouse_vector_search_example(\n",
|
||||
" id Nullable(String),\n",
|
||||
" document Nullable(String),\n",
|
||||
" embedding Array(Float32),\n",
|
||||
" metadata JSON,\n",
|
||||
" uuid UUID DEFAULT generateUUIDv4(),\n",
|
||||
" CONSTRAINT cons_vec_len CHECK length(embedding) = 1536,\n",
|
||||
" INDEX vec_idx embedding TYPE annoy(100,'L2Distance') GRANULARITY 1000\n",
|
||||
") ENGINE = MergeTree ORDER BY uuid SETTINGS index_granularity = 8192\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(f\"Clickhouse Table DDL:\\n\\n{docsearch.schema}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f59360c0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Filtering\n",
|
||||
"\n",
|
||||
"You can have direct access to ClickHouse SQL where statement. You can write `WHERE` clause following standard SQL.\n",
|
||||
"\n",
|
||||
"**NOTE**: Please be aware of SQL injection, this interface must not be directly called by end-user.\n",
|
||||
"\n",
|
||||
"If you custimized your `column_map` under your setting, you search with filter like this:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "232055f6",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:29:36.680805Z",
|
||||
"start_time": "2023-06-03T08:29:34.963676Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Inserting data...: 100%|██████████| 42/42 [00:00<00:00, 6939.56it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.vectorstores import Clickhouse, ClickhouseSettings\n",
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"\n",
|
||||
"loader = TextLoader('../../../state_of_the_union.txt')\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()\n",
|
||||
"\n",
|
||||
"for i, d in enumerate(docs):\n",
|
||||
" d.metadata = {'doc_id': i}\n",
|
||||
"\n",
|
||||
"docsearch = Clickhouse.from_documents(docs, embeddings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "ddbcee77",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:29:43.487436Z",
|
||||
"start_time": "2023-06-03T08:29:43.040831Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"0.6779101415357189 {'doc_id': 0} Madam Speaker, Madam...\n",
|
||||
"0.6997970363474885 {'doc_id': 8} And so many families...\n",
|
||||
"0.7044504914336727 {'doc_id': 1} Groups of citizens b...\n",
|
||||
"0.7053558702165094 {'doc_id': 6} And I’m taking robus...\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"meta = docsearch.metadata_column\n",
|
||||
"output = docsearch.similarity_search_with_relevance_scores('What did the president say about Ketanji Brown Jackson?', \n",
|
||||
" k=4, where_str=f\"{meta}.doc_id<10\")\n",
|
||||
"for d, dist in output:\n",
|
||||
" print(dist, d.metadata, d.page_content[:20] + '...')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a359ed74",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deleting your data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "fb6a9d36",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-06-03T08:30:24.822384Z",
|
||||
"start_time": "2023-06-03T08:30:24.798571Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docsearch.drop()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.11.2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user