2024-08-23 08:19:38 +00:00
|
|
|
# RAG - Pinecone - fusion
|
2023-10-26 01:47:42 +00:00
|
|
|
|
2024-08-23 08:19:38 +00:00
|
|
|
This template enables `RAG fusion` using a re-implementation of
|
|
|
|
the project found [here](https://github.com/Raudaschl/rag-fusion).
|
2023-10-26 01:47:42 +00:00
|
|
|
|
2024-08-23 08:19:38 +00:00
|
|
|
It performs multiple query generation and `Reciprocal Rank Fusion`
|
|
|
|
to re-rank search results.
|
2023-10-31 07:06:02 +00:00
|
|
|
|
2024-08-23 08:19:38 +00:00
|
|
|
It uses the `Pinecone` vectorstore and the `OpenAI` chat and embedding models.
|
2023-10-31 07:06:02 +00:00
|
|
|
|
|
|
|
## Environment Setup
|
|
|
|
|
|
|
|
Set the `OPENAI_API_KEY` environment variable to access the OpenAI models.
|
|
|
|
|
|
|
|
## Usage
|
|
|
|
|
|
|
|
To use this package, you should first have the LangChain CLI installed:
|
|
|
|
|
|
|
|
```shell
|
2023-11-03 19:10:32 +00:00
|
|
|
pip install -U langchain-cli
|
2023-10-31 07:06:02 +00:00
|
|
|
```
|
|
|
|
|
|
|
|
To create a new LangChain project and install this as the only package, you can do:
|
|
|
|
|
|
|
|
```shell
|
|
|
|
langchain app new my-app --package rag-fusion
|
|
|
|
```
|
|
|
|
|
|
|
|
If you want to add this to an existing project, you can just run:
|
|
|
|
|
|
|
|
```shell
|
|
|
|
langchain app add rag-fusion
|
|
|
|
```
|
|
|
|
|
|
|
|
And add the following code to your `server.py` file:
|
|
|
|
```python
|
2023-11-03 20:15:29 +00:00
|
|
|
from rag_fusion.chain import chain as rag_fusion_chain
|
2023-10-31 07:06:02 +00:00
|
|
|
|
|
|
|
add_routes(app, rag_fusion_chain, path="/rag-fusion")
|
|
|
|
```
|
|
|
|
|
|
|
|
(Optional) Let's now configure LangSmith.
|
|
|
|
LangSmith will help us trace, monitor and debug LangChain applications.
|
2024-04-12 20:08:10 +00:00
|
|
|
You can sign up for LangSmith [here](https://smith.langchain.com/).
|
2023-10-31 07:06:02 +00:00
|
|
|
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-fusion/playground](http://127.0.0.1:8000/rag-fusion/playground)
|
|
|
|
|
|
|
|
We can access the template from code with:
|
|
|
|
|
|
|
|
```python
|
|
|
|
from langserve.client import RemoteRunnable
|
|
|
|
|
|
|
|
runnable = RemoteRunnable("http://localhost:8000/rag-fusion")
|
|
|
|
```
|