mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
74 lines
2.1 KiB
Markdown
74 lines
2.1 KiB
Markdown
# RAG with Multiple Indexes (Fusion)
|
|
|
|
A QA application that queries multiple domain-specific retrievers and selects the most relevant documents from across all retrieved results.
|
|
|
|
## Environment Setup
|
|
|
|
This application queries PubMed, ArXiv, Wikipedia, and [Kay AI](https://www.kay.ai) (for SEC filings).
|
|
|
|
You will need to create a free Kay AI account and [get your API key here](https://www.kay.ai).
|
|
Then set environment variable:
|
|
|
|
```bash
|
|
export KAY_API_KEY="<YOUR_API_KEY>"
|
|
```
|
|
|
|
## Usage
|
|
|
|
To use this package, you should first have the LangChain CLI installed:
|
|
|
|
```shell
|
|
pip install -U langchain-cli
|
|
```
|
|
|
|
To create a new LangChain project and install this as the only package, you can do:
|
|
|
|
```shell
|
|
langchain app new my-app --package rag-multi-index-fusion
|
|
```
|
|
|
|
If you want to add this to an existing project, you can just run:
|
|
|
|
```shell
|
|
langchain app add rag-multi-index-fusion
|
|
```
|
|
|
|
And add the following code to your `server.py` file:
|
|
```python
|
|
from rag_multi_index_fusion import chain as rag_multi_index_fusion_chain
|
|
|
|
add_routes(app, rag_multi_index_fusion_chain, path="/rag-multi-index-fusion")
|
|
```
|
|
|
|
(Optional) Let's now configure LangSmith.
|
|
LangSmith will help us trace, monitor and debug LangChain applications.
|
|
LangSmith is currently in private beta, you can sign up [here](https://smith.langchain.com/).
|
|
If you don't have access, you can skip this section
|
|
|
|
|
|
```shell
|
|
export LANGCHAIN_TRACING_V2=true
|
|
export LANGCHAIN_API_KEY=<your-api-key>
|
|
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"
|
|
```
|
|
|
|
If you are inside this directory, then you can spin up a LangServe instance directly by:
|
|
|
|
```shell
|
|
langchain serve
|
|
```
|
|
|
|
This will start the FastAPI app with a server is running locally at
|
|
[http://localhost:8000](http://localhost:8000)
|
|
|
|
We can see all templates at [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)
|
|
We can access the playground at [http://127.0.0.1:8000/rag-multi-index-fusion/playground](http://127.0.0.1:8000/rag-multi-index-fusion/playground)
|
|
|
|
We can access the template from code with:
|
|
|
|
```python
|
|
from langserve.client import RemoteRunnable
|
|
|
|
runnable = RemoteRunnable("http://localhost:8000/rag-multi-index-fusion")
|
|
```
|