Phoenix supports tracing Anthropic API calls, and using Anthropic models for LLM as a Judge evaluations.
AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.
Instrument LLM calls to AWS Bedrock via the boto3 client using the BedrockInstrumentor
Streamline workflows across industries with powerful AI agents. Build and deploy automated workflows using any LLM and cloud platform.
Algorithmically optimizing LM prompts and weights.
Vertex AI is a fully-managed, unified AI development platform for building and using generative AI.
Hardware and software platform that delivers exceptional compute speed, quality, and energy efficiency.
Open-source framework for adding validation, safety, and structure to LLM outputs using schema-based constraints
An open-source Python framework that helps developers build LLM-powered custom applications.
smolagents is a minimalist AI agent framework developed by Hugging Face, designed to simplify the creation and deployment of powerful agents with just a few lines of code
Orchestration framework designed to simplify the creation of applications using LLMs.
LiteLLM allows developers to call all LLM APIs using the openAI format.
Simple, flexible data framework for connecting custom data sources to large language models (LLMs).
Streamline workflows with powerful AI agents. Build and deploy using any LLM and cloud platform.
OpenAI provides AI models and API services.
Pinecone is a vector database that can be used to power RAG in various applications.
Generate synthetic test data, evaluate RAG quality, trace retrieval steps, and analyze cluster behavior for RAG pipelines.
Deploy AI apps in seconds with Vercel's AI SDK and Frontend Cloud.
Weaviate is an open source, AI-native vector database.
Get the latest news, expertise, and product updates from Phoenix .
