Phospho is the text analytics platform for LLM apps. Detect issues and extract insights from text messages of your users or your app. Gather user feedback and measure success. Iterate on your app to create the best conversational experience for your users.

Ship your LLM app in production with confidence, and iterate on it with insights from your users.

Learn more in the full documentation.

• Flexible logging
• Automatic evaluation
• Insights extraction
• Data visualization
• Collaboration

The phospho lab is the core analytics component of phospho. The phospho lab helps you run batched evaluations and event detections on your messages.

pip install "phospho[lab]"

Follow the quickstart here.

This repository contains the implementation of the platform frontend, the API backend, and the insights extraction pipeline.

• phospho-python: Python client with analytics engine
• extractor: FastAPI analytics service wrapping the analytics engine
• backend: FastAPI backend
• platform: NextJS frontend
• internal-tools: Platform management tools

Ensure you have the following installed:

• Docker
• Docker Compose

1. Clone the repo:

git clone [email protected]:phospho-app/phospho.git && cd phospho

2. Register to the core external services:

• OpenAI if you do not want to use Ollama
• Cohere optional (the free developer tier is enough for testing purposes)
• Propelauth (the free tier is enough for testing purposes)

3. Create a copy of the .env.example file as a .env.docker files

cp .env.example .env.docker

4. Complete the .env.docker file with secret variables

nano .env.docker # or emacs or vscode or vim

By default, phospho analytics pipeline use OpenAI as their main LLM provider.

To use Ollama, set OVERRIDE_WITH_OLLAMA_MODEL=mistral (or any model) in .env.docker. In this case, theOPENAI_API_KEY variable is not used. You do need to have an Ollama instance set up and running.

5. Launch the project

docker-compose up

6. Start using phospho

Go the platform at http://localhost:3000 to grab your project id and api key. Log your first message :

export PHOSPHO_PROJECT_ID="your_project_id"
export PHOSPHO_API_KEY="your_api_key"
curl -X POST "http://localhost:80/v2/log/$PHOSPHO_PROJECT_ID" -H "Authorization: Bearer $PHOSPHO_API_KEY" -H "Content-Type: application/json" -d '{"batched_log_events": [{"input": "Hi, I just logged my first task to phospho!","output": "Congrats! Keep pushing!"}]}'

Don't forget to specify your backend url when you use the client libraries in your app. By default it's http://localhost:80

To manage the phospho lab evaluations on a collaborative platform, the easiest way is to register to the hosted version.

1. Create a phospho account
2. Install a phospho client: pip install phospho or npm i phospho
3. Create environment variables for PHOSPHO_API_KEY and PHOSPHO_PROJECT_ID
4. Initialize phospho: phospho.init()
5. Log to phospho with phospho.log(input="question", output="answer")

Follow this guide to get started.

This project is licensed under the Apache 2.0 License - see the LICENSE file for details

• phospho Javascript client
• phospho UI React components
• phospho fastassert constrained inference

We welcome contributions from the community. Please refer to our contributing guidelines for more information.