# datapizza-labs/datapizza-ai

Build reliable Gen AI solutions without overhead 🍕

Repository: https://github.com/datapizza-labs/datapizza-ai
Canonical: https://ross.abutalabs.com/products/datapizza-ai
Homepage: http://docs.datapizza.ai/
Language: Python
License: MIT
License Family: permissive
Topics: agent, ai, genai, llm, python
Last push: 2026-05-19T09:35:45+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 74, longevity 26
- inputs: {"age_days": 366, "days_push": 106, "days_rel": 173, "gap_med": 16, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2239, forks 140 (observed 2026-08-28T04:06:29.605032+00:00)

## What it is
Datapizza AI is a Python framework for building production-ready generative AI applications with agents, LLM clients, and RAG pipelines. It offers multi-provider model support (OpenAI, Gemini, Anthropic, Mistral, Azure), document processing, chunking, embeddings, reranking, and OpenTelemetry-based observability.

## Use cases
- build ai agents in python
- create rag pipelines over pdfs and docx
- swap llm providers without rewriting code
- add tracing and observability to llm apps
- chat with documents using embeddings and reranking
- build multi-provider chatbot backends

## When to choose
- you want a lightweight, low-abstraction GenAI framework in Python
- you need vendor-agnostic model swapping across OpenAI, Anthropic, Gemini, Mistral, or Azure
- you want built-in document ingestion, chunking, and reranking for RAG
- you value OpenTelemetry tracing and production observability out of the box

## When to avoid
- you need a mature ecosystem with a large community and extensive third-party integrations
- you require non-Python languages or runtimes
- you prefer heavyweight all-in-one platforms with managed hosting
- your project depends on features not yet covered by its modular components

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, prompt-engineering, chatbot, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: genai, multi-provider, vendor-agnostic, opentelemetry, document-processing, embeddings, reranking, ai-agents, retrieval-augmented-generation

## Member repositories
- datapizza-labs/datapizza-ai (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.605032+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:44:09.209311+00:00, confidence not recorded.
  - readme: https://github.com/datapizza-labs/datapizza-ai (fetched 2026-08-28T04:06:29.605032+00:00, sha 126e804eaf5e)
  - homepage: http://docs.datapizza.ai/ (fetched 2026-08-29T10:24:36.547670+00:00, sha 36c6c3c2e4f9)
- Data as of 2026-08-30T08:39:29.467469+00:00.