langchain/templates/rag-vectara-multiquery/README.md
Erick Friis a26105de8e
vectara rag mq (#13214)
Description: another Vectara template for MultiQuery RAG flow
Twitter handle: @ofermend

Fixes to #13106

---------

Co-authored-by: Ofer Mendelevitch <ofer@vectara.com>
Co-authored-by: Ofer Mendelevitch <ofermend@gmail.com>
2023-11-10 10:08:45 -08:00

73 lines
1.9 KiB
Markdown

# rag-vectara-multiquery
This template performs multiquery RAG with vectara.
## Environment Setup
Set the `OPENAI_API_KEY` environment variable to access the OpenAI models.
Also, ensure the following environment variables are set:
* `VECTARA_CUSTOMER_ID`
* `VECTARA_CORPUS_ID`
* `VECTARA_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-vectara
```
If you want to add this to an existing project, you can just run:
```shell
langchain app add rag-vectara
```
And add the following code to your `server.py` file:
```python
from rag_vectara import chain as rag_vectara_chain
add_routes(app, rag_vectara_chain, path="/rag-vectara")
```
(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 "vectara-demo"
```
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-vectara/playground](http://127.0.0.1:8000/rag-vectara/playground)
We can access the template from code with:
```python
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/rag-vectara")
```