pdx-labs/pdx

Prompt Engineering and Dev-Ops toolkit for applications powered by Language Models

Hello, I'm PDX 👋

PDX is a framework for prompt engineering and a dev-ops toolkit.

At the core, it provides a mental-model on how to build and manage agents. An agent is a collection of prompts and/or prompt templates with information that is used to interact with the Language Models.

Documentation: pdxlabs.io/docs

Website: pdxlabs.io

Quickstart: create-an-agent

Installation

pip install pdx

Quickstart

To create your first agent, run the following command:

pdx create my_first_agent

Run and test out the agent by running:

pdx test my_first_agent --verbose

More information here: PDX - Main Concepts

Why use PDX?

• 🗃️ Low dependency footprint -> ease of production deployment and maintainance.
• 📂 Mental model to separate prompt templates from the application code. (Similar to Flask blueprint or FastAPI router).
• 📌 Version control the prompts along with their evaluation metrics.
• 📸 Logging and tracing of inputs, prompt render, and model response made easy.
• 🧯 Standardize Error handling and logging.
• 💾 Caching for lowering latency. (Coming soon)
• 📊 Observability out-of-the-box. (Coming soon)
• 📩 Log feedback of the user. (Coming soon)
• 🛎️ A/B testing of prompts. (Coming soon)

Demos

Check our the demos in the demos repository.

Models (APIs) currently supported:

• OpenAI
• Anthropic
• Cohere
• Eleven Labs

pdx's Issues

Update Anthropic Client

Anthropic changed their python sdk - making this code line outdated.

https://github.com/pdx-labs/pdx/blob/355027c89f6de7463ceabc6d698452ad7a4fa742/src/pdx/models/anthropic/completion.py#L24C23-L24C23

---

Would love to know if this might help - https://github.com/BerriAI/litellm

~Simple I/O library, that standardizes all the llm api calls to the OpenAI call

from litellm import completion

## set ENV variables
# ENV variables can be set in .env file, too. Example in .env.example
os.environ["OPENAI_API_KEY"] = "openai key"
os.environ["ANTHROPIC_API_KEY"] = "anthropic key"

messages = [{ "content": "Hello, how are you?","role": "user"}]

# openai call
response = completion(model="gpt-3.5-turbo", messages=messages)

# anthropic call
response = completion("claude-v-2", messages)