langchain/docs/extras/ecosystem/integrations/infino.mdx
Naman Modi 37a89918e0
Infino integration for simplified logs, metrics & search across LLM data & token usage (#6218)
### Integration of Infino with LangChain for Enhanced Observability

This PR aims to integrate [Infino](https://github.com/infinohq/infino),
an open source observability platform written in rust for storing
metrics and logs at scale, with LangChain, providing users with a
streamlined and efficient method of tracking and recording LangChain
experiments. By incorporating Infino into LangChain, users will be able
to gain valuable insights and easily analyze the behavior of their
language models.

#### Please refer to the following files related to integration:
- `InfinoCallbackHandler`: A [callback
handler](https://github.com/naman-modi/langchain/blob/feature/infino-integration/langchain/callbacks/infino_callback.py)
specifically designed for storing chain responses within Infino.
- Example `infino.ipynb` file: A comprehensive notebook named
[infino.ipynb](https://github.com/naman-modi/langchain/blob/feature/infino-integration/docs/extras/modules/callbacks/integrations/infino.ipynb)
has been included to guide users on effectively leveraging Infino for
tracking LangChain requests.
- [Integration
Doc](https://github.com/naman-modi/langchain/blob/feature/infino-integration/docs/extras/ecosystem/integrations/infino.mdx)
for Infino integration.

By integrating Infino, LangChain users will gain access to powerful
visualization and debugging capabilities. Infino enables easy tracking
of inputs, outputs, token usage, execution time of LLMs. This
comprehensive observability ensures a deeper understanding of individual
executions and facilitates effective debugging.

Co-authors: @vinaykakade @savannahar68
---------

Co-authored-by: Vinay Kakade <vinaykakade@gmail.com>
2023-06-21 01:38:20 -07:00

36 lines
1.2 KiB
Plaintext

# Infino
>[Infino](https://github.com/infinohq/infino) is an open-source observability platform that stores both metrics and application logs together.
Key features of infino include:
- Metrics Tracking: Capture time taken by LLM model to handle request, errors, number of tokens, and costing indication for the particular LLM.
- Data Tracking: Log and store prompt, request, and response data for each LangChain interaction.
- Graph Visualization: Generate basic graphs over time, depicting metrics such as request duration, error occurrences, token count, and cost.
## Installation and Setup
First, you'll need to install the `infinopy` Python package as follows:
```bash
pip install infinopy
```
If you already have an Infino Server running, then you're good to go; but if
you don't, follow the next steps to start it:
- Make sure you have Docker installed
- Run the following in your terminal:
```
docker run --rm --detach --name infino-example -p 3000:3000 infinohq/infino:latest
```
## Using Infino
See a [usage example of `InfinoCallbackHandler`](/docs/modules/callbacks/integrations/infino.html).
```python
from langchain.callbacks import InfinoCallbackHandler
```