langchain/templates/retrieval-agent-fireworks/README.md
Erick Friis 1183769cf7
template: tool-retrieval-fireworks (#17052)
- Initial commit oss-tool-retrieval-agent
- README update
- lint
- lock
- format imports
- Rename to retrieval-agent-fireworks
- cr

<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes if applicable,
  - **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Taqi Jaffri <tjaffri@docugami.com>
2024-02-05 11:50:17 -08:00

73 lines
2.4 KiB
Markdown

# retrieval-agent-fireworks
This package uses open source models hosted on FireworksAI to do retrieval using an agent architecture. By default, this does retrieval over Arxiv.
We will use `Mixtral8x7b-instruct-v0.1`, which is shown in this blog to yield reasonable
results with function calling even though it is not fine tuned for this task: https://huggingface.co/blog/open-source-llms-as-agents
## Environment Setup
There are various great ways to run OSS models. We will use FireworksAI as an easy way to run the models. See [here](https://python.langchain.com/docs/integrations/providers/fireworks) for more information.
Set the `FIREWORKS_API_KEY` environment variable to access Fireworks.
## 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 retrieval-agent-fireworks
```
If you want to add this to an existing project, you can just run:
```shell
langchain app add retrieval-agent-fireworks
```
And add the following code to your `server.py` file:
```python
from retrieval_agent_fireworks import chain as retrieval_agent_fireworks_chain
add_routes(app, retrieval_agent_fireworks_chain, path="/retrieval-agent-fireworks")
```
(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/retrieval-agent-fireworks/playground](http://127.0.0.1:8000/retrieval-agent-fireworks/playground)
We can access the template from code with:
```python
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/retrieval-agent-fireworks")
```