-
Notifications
You must be signed in to change notification settings - Fork 17
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Propose the following README updates for further clarity
- Loading branch information
Showing
2 changed files
with
34 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,3 +1,4 @@ | ||
.DS_Store | ||
.vscode | ||
__pycache__ | ||
.coverage | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,10 +1,41 @@ | ||
# langchain-weaviate | ||
|
||
This package contains the LangChain integrations for Weaviate through their `weaviate-client` SDK. | ||
## About | ||
|
||
This package contains the [Weaviate](https://github.com/weaviate/weaviate) integrations for [LangChain](https://github.com/langchain-ai/langchain). | ||
|
||
- **Weaviate** is an open source, AI-native vector database that helps developers create intuitive and reliable AI-powered applications. | ||
- **LangChain** is a framework for developing applications powered by language models. | ||
|
||
Using this package, LangChain users can conveniently set Weaviate as their vector store to store and retrieve embeddings. | ||
|
||
## Requirements | ||
|
||
To use this package, you need to have a running Weaviate instance. | ||
|
||
Weaviate can be [deployed in many different ways](https://weaviate.io/developers/weaviate/starter-guides/which-weaviate) such as in containerized environments, on Kubernetes, or in the cloud as a managed service, on-premises, or through a cloud provider such as AWS or Google Cloud. | ||
|
||
The deployment method to choose depends on your use case and infrastructure requirements. | ||
|
||
Two of the most common ways to deploy Weaviate are: | ||
- [Docker Compose](https://weaviate.io/developers/weaviate/installation/docker-compose) | ||
- [Weaviate Cloud Services (WCS)](https://console.weaviate.cloud) | ||
|
||
## Installation and Setup | ||
|
||
- Install the LangChain partner package | ||
As an integration package, this assumes you have already installed LangChain. If not, please refer to the [LangChain installation guide](https://python.langchain.com/docs/get_started/installation). | ||
|
||
Then, install this package: | ||
|
||
```bash | ||
pip install langchain-weaviate | ||
``` | ||
|
||
## Usage | ||
|
||
Please see the included [Jupyter notebook](docs/vectorstores.ipynb) for an example of how to use this package. | ||
|
||
## Further resources | ||
|
||
- [LangChain documentation](https://python.langchain.com/docs) | ||
- [Weaviate documentation](https://weaviate.io/developers/weaviate) |