mirror of https://github.com/hwchase17/langchain
Feature: Add support for meilisearch vectorstore (#7649)
**Description:** Add support for Meilisearch vector store. Resolve #7603 - No external dependencies added - A notebook has been added @rlancemartin https://twitter.com/meilisearch Co-authored-by: Bagatur <baskaryan@gmail.com>pull/8441/head
Amélie
1 year ago
committed by
GitHub
parent
b7d6e1909c
commit
8ee56b9a5b
@ -0,0 +1,306 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Meilisearch\n",
|
||||
"\n",
|
||||
"> [Meilisearch](https://meilisearch.com) is an open-source, lightning-fast, and hyper relevant search engine. It comes with great defaults to help developers build snappy search experiences. \n",
|
||||
">\n",
|
||||
"> You can [self-host Meilisearch](https://www.meilisearch.com/docs/learn/getting_started/installation#local-installation) or run on [Meilisearch Cloud](https://www.meilisearch.com/pricing).\n",
|
||||
"\n",
|
||||
"Meilisearch v1.3 supports vector search. This page guides you through integrating Meilisearch as a vector store and using it to perform vector search."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"### Launching a Meilisearch instance\n",
|
||||
"\n",
|
||||
"You will need a running Meilisearch instance to use as your vector store. You can run [Meilisearch in local](https://www.meilisearch.com/docs/learn/getting_started/installation#local-installation) or create a [Meilisearch Cloud](https://cloud.meilisearch.com/) account.\n",
|
||||
"\n",
|
||||
"As of Meilisearch v1.3, vector storage is an experimental feature. After launching your Meilisearch instance, you need to **enable vector storage**. For self-hosted Meilisearch, read the docs on [enabling experimental features](https://www.meilisearch.com/docs/learn/experimental/vector-search). On **Meilisearch Cloud**, enable _Vector Store_ via your project _Settings_ page.\n",
|
||||
"\n",
|
||||
"You should now have a running Meilisearch instance with vector storage enabled. 🎉\n",
|
||||
"\n",
|
||||
"### Credentials\n",
|
||||
"\n",
|
||||
"To interact with your Meilisearch instance, the Meilisearch SDK needs a host (URL of your instance) and an API key.\n",
|
||||
"\n",
|
||||
"**Host**\n",
|
||||
"\n",
|
||||
"- In **local**, the default host is `localhost:7700`\n",
|
||||
"- On **Meilisearch Cloud**, find the host in your project _Settings_ page\n",
|
||||
"\n",
|
||||
"**API keys**\n",
|
||||
"\n",
|
||||
"Meilisearch instance provides you with three API keys out of the box: \n",
|
||||
"- A `MASTER KEY` — it should only be used to create your Meilisearch instance\n",
|
||||
"- A `ADMIN KEY` — use it only server-side to update your database and its settings\n",
|
||||
"- A `SEARCH KEY` — a key that you can safely share in front-end applications\n",
|
||||
"\n",
|
||||
"You can create [additional API keys](https://www.meilisearch.com/docs/learn/security/master_api_keys) as needed."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Installing dependencies\n",
|
||||
"\n",
|
||||
"This guide uses the [Meilisearch Python SDK](https://github.com/meilisearch/meilisearch-python). You can install it by running:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install meilisearch"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"For more information, refer to the [Meilisearch Python SDK documentation](https://meilisearch.github.io/meilisearch-python/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Examples\n",
|
||||
"\n",
|
||||
"There are multiple ways to initialize the Meilisearch vector store: providing a Meilisearch client or the _URL_ and _API key_ as needed. In our examples, the credentials will be loaded from the environment.\n",
|
||||
"\n",
|
||||
"You can make environment variables available in your Notebook environment by using `os` and `getpass`. You can use this technique for all the following examples."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"os.environ[\"MEILI_HTTP_ADDR\"] = getpass.getpass(\"Meilisearch HTTP address and port:\")\n",
|
||||
"os.environ[\"MEILI_MASTER_KEY\"] = getpass.getpass(\"Meilisearch API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We want to use OpenAIEmbeddings so we have to get the OpenAI API Key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Adding text and embeddings\n",
|
||||
"\n",
|
||||
"This example adds text to the Meilisearch vector database without having to initialize a Meilisearch vector store."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.vectorstores import Meilisearch\n",
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open(\"../../../state_of_the_union.txt\") as f:\n",
|
||||
" state_of_the_union = f.read()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"texts = text_splitter.split_text(state_of_the_union)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Use Meilisearch vector store to store texts & associated embeddings as vector\n",
|
||||
"vector_store = Meilisearch.from_texts(texts=texts, embedding=embeddings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Behind the scenes, Meilisearch will convert the text to multiple vectors. This will bring us to the same result as the following example."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Adding documents and embeddings\n",
|
||||
"\n",
|
||||
"In this example, we'll use Langchain TextSplitter to split the text in multiple documents. Then, we'll store these documents along with their embeddings."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"\n",
|
||||
"# Load text\n",
|
||||
"loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"\n",
|
||||
"# Create documents\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"# Import documents & embeddings in the vector store\n",
|
||||
"vector_store = Meilisearch.from_documents(documents=documents, embedding=embeddings)\n",
|
||||
"\n",
|
||||
"# Search in our vector store\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = vector_store.similarity_search(query)\n",
|
||||
"print(docs[0].page_content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Add documents by creating a Meilisearch Vectorstore"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In this approach, we create a vector store object and add documents to it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.vectorstores import Meilisearch\n",
|
||||
"import meilisearch\n",
|
||||
"\n",
|
||||
"client = meilisearch.Client(url=\"http://127.0.0.1:7700\", api_key=\"***\")\n",
|
||||
"vector_store = Meilisearch(\n",
|
||||
" embedding=embeddings, client=client, index_name=\"langchain_demo\", text_key=\"text\"\n",
|
||||
")\n",
|
||||
"vector_store.add_documents(documents)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Similarity Search with score\n",
|
||||
"\n",
|
||||
"This specific method allows you to return the documents and the distance score of the query to them."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs_and_scores = vector_store.similarity_search_with_score(query)\n",
|
||||
"docs_and_scores[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Similarity Search by vector"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embedding_vector = embeddings.embed_query(query)\n",
|
||||
"docs_and_scores = vector_store.similarity_search_by_vector(embedding_vector)\n",
|
||||
"docs_and_scores[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Additional resources\n",
|
||||
"\n",
|
||||
"Documentation\n",
|
||||
"- [Meilisearch](https://www.meilisearch.com/docs/)\n",
|
||||
"- [Meilisearch Python SDK](https://python-sdk.meilisearch.com)\n",
|
||||
"\n",
|
||||
"Open-source repositories\n",
|
||||
"- [Meilisearch repository](https://github.com/meilisearch/meilisearch)\n",
|
||||
"- [Meilisearch Python SDK](https://github.com/meilisearch/meilisearch-python)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.11.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@ -0,0 +1,312 @@
|
||||
"""Wrapper around Meilisearch vector database."""
|
||||
from __future__ import annotations
|
||||
|
||||
import uuid
|
||||
from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Tuple, Type
|
||||
|
||||
from langchain.docstore.document import Document
|
||||
from langchain.embeddings.base import Embeddings
|
||||
from langchain.utils import get_from_env
|
||||
from langchain.vectorstores.base import VectorStore
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from meilisearch import Client
|
||||
|
||||
|
||||
def _create_client(
|
||||
client: Optional[Client] = None,
|
||||
url: Optional[str] = None,
|
||||
api_key: Optional[str] = None,
|
||||
) -> Client:
|
||||
try:
|
||||
import meilisearch
|
||||
except ImportError:
|
||||
raise ValueError(
|
||||
"Could not import meilisearch python package. "
|
||||
"Please install it with `pip install meilisearch`."
|
||||
)
|
||||
if not client:
|
||||
url = url or get_from_env("url", "MEILI_HTTP_ADDR")
|
||||
try:
|
||||
api_key = api_key or get_from_env("api_key", "MEILI_MASTER_KEY")
|
||||
except Exception:
|
||||
pass
|
||||
client = meilisearch.Client(url=url, api_key=api_key)
|
||||
elif not isinstance(client, meilisearch.Client):
|
||||
raise ValueError(
|
||||
f"client should be an instance of meilisearch.Client, "
|
||||
f"got {type(client)}"
|
||||
)
|
||||
try:
|
||||
client.version()
|
||||
except ValueError as e:
|
||||
raise ValueError(f"Failed to connect to Meilisearch: {e}")
|
||||
return client
|
||||
|
||||
|
||||
class Meilisearch(VectorStore):
|
||||
"""Initialize wrapper around Meilisearch vector database.
|
||||
|
||||
To use this, you need to have `meilisearch` python package installed,
|
||||
and a running Meilisearch instance.
|
||||
|
||||
To learn more about Meilisearch Python, refer to the in-depth
|
||||
Meilisearch Python documentation: https://meilisearch.github.io/meilisearch-python/.
|
||||
|
||||
See the following documentation for how to run a Meilisearch instance:
|
||||
https://www.meilisearch.com/docs/learn/getting_started/quick_start.
|
||||
|
||||
Example:
|
||||
.. code-block:: python
|
||||
|
||||
from langchain.vectorstores import Meilisearch
|
||||
from langchain.embeddings.openai import OpenAIEmbeddings
|
||||
import meilisearch
|
||||
|
||||
# api_key is optional; provide it if your meilisearch instance requires it
|
||||
client = meilisearch.Client(url='http://127.0.0.1:7700', api_key='***')
|
||||
embeddings = OpenAIEmbeddings()
|
||||
vectorstore = Meilisearch(
|
||||
embedding=embeddings,
|
||||
client=client,
|
||||
index_name='langchain_demo',
|
||||
text_key='text')
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
embedding: Embeddings,
|
||||
client: Optional[Client] = None,
|
||||
url: Optional[str] = None,
|
||||
api_key: Optional[str] = None,
|
||||
index_name: str = "langchain-demo",
|
||||
text_key: str = "text",
|
||||
metadata_key: str = "metadata",
|
||||
):
|
||||
"""Initialize with Meilisearch client."""
|
||||
client = _create_client(client=client, url=url, api_key=api_key)
|
||||
|
||||
self._client = client
|
||||
self._index_name = index_name
|
||||
self._embedding = embedding
|
||||
self._text_key = text_key
|
||||
self._metadata_key = metadata_key
|
||||
|
||||
def add_texts(
|
||||
self,
|
||||
texts: Iterable[str],
|
||||
metadatas: Optional[List[dict]] = None,
|
||||
ids: Optional[List[str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[str]:
|
||||
"""Run more texts through the embedding and add them to the vector store.
|
||||
|
||||
Args:
|
||||
texts (Iterable[str]): Iterable of strings/text to add to the vectorstore.
|
||||
metadatas (Optional[List[dict]]): Optional list of metadata.
|
||||
Defaults to None.
|
||||
ids Optional[List[str]]: Optional list of IDs.
|
||||
Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[str]: List of IDs of the texts added to the vectorstore.
|
||||
"""
|
||||
texts = list(texts)
|
||||
|
||||
# Embed and create the documents
|
||||
docs = []
|
||||
if ids is None:
|
||||
ids = [uuid.uuid4().hex for _ in texts]
|
||||
if metadatas is None:
|
||||
metadatas = [{} for _ in texts]
|
||||
embedding_vectors = self._embedding.embed_documents(texts)
|
||||
|
||||
for i, text in enumerate(texts):
|
||||
id = ids[i]
|
||||
metadata = metadatas[i]
|
||||
metadata[self._text_key] = text
|
||||
embedding = embedding_vectors[i]
|
||||
docs.append(
|
||||
{
|
||||
"id": id,
|
||||
"_vectors": embedding,
|
||||
f"{self._metadata_key}": metadata,
|
||||
}
|
||||
)
|
||||
|
||||
# Send to Meilisearch
|
||||
self._client.index(str(self._index_name)).add_documents(docs)
|
||||
return ids
|
||||
|
||||
def similarity_search(
|
||||
self,
|
||||
query: str,
|
||||
k: int = 4,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return meilisearch documents most similar to the query.
|
||||
|
||||
Args:
|
||||
query (str): Query text for which to find similar documents.
|
||||
k (int): Number of documents to return. Defaults to 4.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata.
|
||||
Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Document]: List of Documents most similar to the query
|
||||
text and score for each.
|
||||
"""
|
||||
docs_and_scores = self.similarity_search_with_score(
|
||||
query=query,
|
||||
k=k,
|
||||
filter=filter,
|
||||
kwargs=kwargs,
|
||||
)
|
||||
return [doc for doc, _ in docs_and_scores]
|
||||
|
||||
def similarity_search_with_score(
|
||||
self,
|
||||
query: str,
|
||||
k: int = 4,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Tuple[Document, float]]:
|
||||
"""Return meilisearch documents most similar to the query, along with scores.
|
||||
|
||||
Args:
|
||||
query (str): Query text for which to find similar documents.
|
||||
k (int): Number of documents to return. Defaults to 4.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata.
|
||||
Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Document]: List of Documents most similar to the query
|
||||
text and score for each.
|
||||
"""
|
||||
_query = self._embedding.embed_query(query)
|
||||
|
||||
docs = self.similarity_search_by_vector_with_scores(
|
||||
embedding=_query,
|
||||
k=k,
|
||||
filter=filter,
|
||||
kwargs=kwargs,
|
||||
)
|
||||
return docs
|
||||
|
||||
def similarity_search_by_vector_with_scores(
|
||||
self,
|
||||
embedding: List[float],
|
||||
k: int = 4,
|
||||
filter: Optional[Dict[str, Any]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Tuple[Document, float]]:
|
||||
"""Return meilisearch documents most similar to embedding vector.
|
||||
|
||||
Args:
|
||||
embedding (List[float]): Embedding to look up similar documents.
|
||||
k (int): Number of documents to return. Defaults to 4.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata.
|
||||
Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Document]: List of Documents most similar to the query
|
||||
vector and score for each.
|
||||
"""
|
||||
docs = []
|
||||
results = self._client.index(str(self._index_name)).search(
|
||||
"", {"vector": embedding, "limit": k, "filter": filter}
|
||||
)
|
||||
|
||||
for result in results["hits"]:
|
||||
metadata = result[self._metadata_key]
|
||||
if self._text_key in metadata:
|
||||
text = metadata.pop(self._text_key)
|
||||
semantic_score = result["_semanticScore"]
|
||||
docs.append(
|
||||
(Document(page_content=text, metadata=metadata), semantic_score)
|
||||
)
|
||||
|
||||
return docs
|
||||
|
||||
def similarity_search_by_vector(
|
||||
self,
|
||||
embedding: List[float],
|
||||
k: int = 4,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return meilisearch documents most similar to embedding vector.
|
||||
|
||||
Args:
|
||||
embedding (List[float]): Embedding to look up similar documents.
|
||||
k (int): Number of documents to return. Defaults to 4.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata.
|
||||
Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Document]: List of Documents most similar to the query
|
||||
vector and score for each.
|
||||
"""
|
||||
docs = self.similarity_search_by_vector_with_scores(
|
||||
embedding=embedding,
|
||||
k=k,
|
||||
filter=filter,
|
||||
kwargs=kwargs,
|
||||
)
|
||||
return [doc for doc, _ in docs]
|
||||
|
||||
@classmethod
|
||||
def from_texts(
|
||||
cls: Type[Meilisearch],
|
||||
texts: List[str],
|
||||
embedding: Embeddings,
|
||||
metadatas: Optional[List[dict]] = None,
|
||||
client: Optional[Client] = None,
|
||||
url: Optional[str] = None,
|
||||
api_key: Optional[str] = None,
|
||||
index_name: str = "langchain-demo",
|
||||
ids: Optional[List[str]] = None,
|
||||
text_key: Optional[str] = "text",
|
||||
metadata_key: Optional[str] = "metadata",
|
||||
**kwargs: Any,
|
||||
) -> Meilisearch:
|
||||
"""Construct Meilisearch wrapper from raw documents.
|
||||
|
||||
This is a user-friendly interface that:
|
||||
1. Embeds documents.
|
||||
2. Adds the documents to a provided Meilisearch index.
|
||||
|
||||
This is intended to be a quick way to get started.
|
||||
|
||||
Example:
|
||||
.. code-block:: python
|
||||
|
||||
from langchain import Meilisearch
|
||||
from langchain.embeddings import OpenAIEmbeddings
|
||||
import meilisearch
|
||||
|
||||
# The environment should be the one specified next to the API key
|
||||
# in your Meilisearch console
|
||||
client = meilisearch.Client(url='http://127.0.0.1:7700', api_key='***')
|
||||
embeddings = OpenAIEmbeddings()
|
||||
docsearch = Meilisearch.from_texts(
|
||||
client=client,
|
||||
embeddings=embeddings,
|
||||
)
|
||||
"""
|
||||
client = _create_client(client=client, url=url, api_key=api_key)
|
||||
|
||||
vectorstore = cls(
|
||||
embedding=embedding,
|
||||
client=client,
|
||||
index_name=index_name,
|
||||
)
|
||||
vectorstore.add_texts(
|
||||
texts=texts,
|
||||
metadatas=metadatas,
|
||||
ids=ids,
|
||||
text_key=text_key,
|
||||
metadata_key=metadata_key,
|
||||
)
|
||||
return vectorstore
|
||||
@ -0,0 +1,17 @@
|
||||
version: "3.8"
|
||||
|
||||
services:
|
||||
meilisearch:
|
||||
image: getmeili/meilisearch:latest
|
||||
environment:
|
||||
- MEILI_MASTER_KEY=${MEILI_MASTER_KEY:-masterKey}
|
||||
- MEILI_NO_ANALYTICS=${MEILI_NO_ANALYTICS:-true}
|
||||
- MEILI_ENV=${MEILI_ENV:-development}
|
||||
ports:
|
||||
- ${MEILI_PORT:-7700}:7700
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-f", "http://localhost:7700"]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 5
|
||||
@ -0,0 +1,143 @@
|
||||
"""Test Meilisearch functionality."""
|
||||
from typing import Generator
|
||||
|
||||
import meilisearch
|
||||
import pytest
|
||||
import requests
|
||||
|
||||
from langchain.docstore.document import Document
|
||||
from langchain.vectorstores import Meilisearch
|
||||
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
|
||||
|
||||
INDEX_NAME = "test-langchain-demo"
|
||||
TEST_MEILI_HTTP_ADDR = "http://localhost:7700"
|
||||
TEST_MEILI_MASTER_KEY = "masterKey"
|
||||
|
||||
|
||||
class TestMeilisearchVectorSearch:
|
||||
@pytest.fixture(scope="class", autouse=True)
|
||||
def enable_vector_search(self) -> Generator[str, None, None]:
|
||||
requests.patch(
|
||||
f"{TEST_MEILI_HTTP_ADDR}/experimental-features",
|
||||
headers={"Authorization": f"Bearer {TEST_MEILI_MASTER_KEY}"},
|
||||
json={"vectorStore": True},
|
||||
timeout=10,
|
||||
)
|
||||
yield "done"
|
||||
requests.patch(
|
||||
f"{TEST_MEILI_HTTP_ADDR}/experimental-features",
|
||||
headers={"Authorization": f"Bearer {TEST_MEILI_MASTER_KEY}"},
|
||||
json={"vectorStore": False},
|
||||
timeout=10,
|
||||
)
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def setup(self) -> None:
|
||||
self.delete_all_indexes()
|
||||
|
||||
@pytest.fixture(scope="class", autouse=True)
|
||||
def teardown_test(self) -> Generator[str, None, None]:
|
||||
# Yields back to the test function.
|
||||
yield "done"
|
||||
self.delete_all_indexes()
|
||||
|
||||
def delete_all_indexes(self) -> None:
|
||||
client = self.client()
|
||||
# Deletes all the indexes in the Meilisearch instance.
|
||||
indexes = client.get_indexes()
|
||||
for index in indexes["results"]:
|
||||
task = client.index(index.uid).delete()
|
||||
client.wait_for_task(task.task_uid)
|
||||
|
||||
def client(self) -> meilisearch.Client:
|
||||
return meilisearch.Client(TEST_MEILI_HTTP_ADDR, TEST_MEILI_MASTER_KEY)
|
||||
|
||||
def _wait_last_task(self) -> None:
|
||||
client = self.client()
|
||||
# Get the last task
|
||||
tasks = client.get_tasks()
|
||||
# Wait for the last task to be completed
|
||||
client.wait_for_task(tasks.results[0].uid)
|
||||
|
||||
def test_meilisearch(self) -> None:
|
||||
"""Test end to end construction and search."""
|
||||
texts = ["foo", "bar", "baz"]
|
||||
vectorstore = Meilisearch.from_texts(
|
||||
texts=texts,
|
||||
embedding=FakeEmbeddings(),
|
||||
url=TEST_MEILI_HTTP_ADDR,
|
||||
api_key=TEST_MEILI_MASTER_KEY,
|
||||
index_name=INDEX_NAME,
|
||||
)
|
||||
self._wait_last_task()
|
||||
output = vectorstore.similarity_search("foo", k=1)
|
||||
assert output == [Document(page_content="foo")]
|
||||
|
||||
def test_meilisearch_with_client(self) -> None:
|
||||
"""Test end to end construction and search."""
|
||||
texts = ["foo", "bar", "baz"]
|
||||
vectorstore = Meilisearch.from_texts(
|
||||
texts=texts,
|
||||
embedding=FakeEmbeddings(),
|
||||
client=self.client(),
|
||||
index_name=INDEX_NAME,
|
||||
)
|
||||
self._wait_last_task()
|
||||
output = vectorstore.similarity_search("foo", k=1)
|
||||
assert output == [Document(page_content="foo")]
|
||||
|
||||
def test_meilisearch_with_metadatas(self) -> None:
|
||||
"""Test end to end construction and search."""
|
||||
texts = ["foo", "bar", "baz"]
|
||||
metadatas = [{"page": i} for i in range(len(texts))]
|
||||
docsearch = Meilisearch.from_texts(
|
||||
texts=texts,
|
||||
embedding=FakeEmbeddings(),
|
||||
url=TEST_MEILI_HTTP_ADDR,
|
||||
api_key=TEST_MEILI_MASTER_KEY,
|
||||
index_name=INDEX_NAME,
|
||||
metadatas=metadatas,
|
||||
)
|
||||
self._wait_last_task()
|
||||
output = docsearch.similarity_search("foo", k=1)
|
||||
assert len(output) == 1
|
||||
assert output[0].page_content == "foo"
|
||||
assert output[0].metadata["page"] == 0
|
||||
assert output == [Document(page_content="foo", metadata={"page": 0})]
|
||||
|
||||
def test_meilisearch_with_metadatas_with_scores(self) -> None:
|
||||
"""Test end to end construction and scored search."""
|
||||
texts = ["foo", "bar", "baz"]
|
||||
metadatas = [{"page": str(i)} for i in range(len(texts))]
|
||||
docsearch = Meilisearch.from_texts(
|
||||
texts=texts,
|
||||
embedding=FakeEmbeddings(),
|
||||
url=TEST_MEILI_HTTP_ADDR,
|
||||
api_key=TEST_MEILI_MASTER_KEY,
|
||||
index_name=INDEX_NAME,
|
||||
metadatas=metadatas,
|
||||
)
|
||||
self._wait_last_task()
|
||||
output = docsearch.similarity_search_with_score("foo", k=1)
|
||||
assert output == [(Document(page_content="foo", metadata={"page": "0"}), 9.0)]
|
||||
|
||||
def test_meilisearch_with_metadatas_with_scores_using_vector(self) -> None:
|
||||
"""Test end to end construction and scored search, using embedding vector."""
|
||||
texts = ["foo", "bar", "baz"]
|
||||
metadatas = [{"page": str(i)} for i in range(len(texts))]
|
||||
embeddings = FakeEmbeddings()
|
||||
|
||||
docsearch = Meilisearch.from_texts(
|
||||
texts=texts,
|
||||
embedding=FakeEmbeddings(),
|
||||
url=TEST_MEILI_HTTP_ADDR,
|
||||
api_key=TEST_MEILI_MASTER_KEY,
|
||||
index_name=INDEX_NAME,
|
||||
metadatas=metadatas,
|
||||
)
|
||||
embedded_query = embeddings.embed_query("foo")
|
||||
self._wait_last_task()
|
||||
output = docsearch.similarity_search_by_vector_with_scores(
|
||||
embedding=embedded_query, k=1
|
||||
)
|
||||
assert output == [(Document(page_content="foo", metadata={"page": "0"}), 9.0)]
|
||||
Loading…
Reference in New Issue