🧪 phospho is the backoffice for your LLM app.
Detect issues and extract insights from your users' text messages.
Gather feedback and measure success. Create the best conversational experience for your users. Analyze logs effortlessly and finally make sense of all your data.
Learn more in the documentation.
phospho_demo_socials.mp4
- Clustering: Group similar conversations and identify patterns
- A/B Testing: Compare different versions of your LLM app
- Data Labeling: Efficiently categorize and annotate your data
- User Analytics: Gain insights into user behavior and preferences
- Integration: Sync data with LangSmith/Langfuse, Argilla, PowerBI
- Data Visualization: Powerful tools to understand your data
- Multi-user Experience: Collaborate with your team seamlessly
Quickly import, analyze and label data on the phospho platform.
- Create an account
- Install our SDK:
- Python:
pip install phospho - JavaScript:
npm i phospho
- Set environment variables ( you can find these on your phospho account )
PHOSPHO_API_KEYPHOSPHO_PROJECT_ID
- Initialize phospho:
phospho.init() - Start logging to phospho with
phospho.log(input="question", output="answer")
Follow this guide to get started.
Note:
- You can also import data directly through a CSV or Excel directly on the platform
- If you use the python version, you might want to disable auto-logging with
phospho.init(auto_log=False)
Create a .env.docker using this guide. Then, run:
docker compose upGo to localhost:3000 to see the platform frontend. The backend documentation is available at localhost:8000/v3/docs.
We welcome contributions from the community. Please refer to our contributing guidelines for more information.
This project uses Python3.11+ and NextJS.
To work on it locally,
- Make sure you have properly added
.envfiles inai-hub,extractor,backend,platform. - Install the Temporal CLI
brew install temporal - Create a python virtual environment.
python -m venv .venv
source .venv/bin/activate- Then, the quickest way to get started is to use the makefile to install and up.
# Install dependencies
make install
# Launch everything
make up-
Go to
localhost:3000to see the platform frontend. The backend documentations are available atlocalhost:8000/api/docs,localhost:8000/v2/docsandlocalhost:8000/v3/docs. -
To stop everything, run:
make stop- AI chat bubble with Mistral - custom AI assistant connected to your knowledge
- chatbot template streamlit OpenAI
- phospho Javascript client
- phospho UI React components for user feedback
This project is licensed under the Apache 2.0 License - see the LICENSE file for details
We are a team of passionate AI builders, feel free to reach out here. With love and baguettes from Paris, the phospho team 🥖💚
