1 Repo
Standardizing the format of real-time chat completion events across different model providers.
Distinct from Conversation Format Normalization: Focuses specifically on LLM chat stream events rather than general dialogue dataset structure.
Explore 1 awesome GitHub repository matching data & databases · Chat Completion Stream Normalization. Refine with filters or upvote what's useful.
AdalFlow is an autonomous AI agent framework and LLM application library designed for building modular workflows. It serves as a model-agnostic interface and RAG pipeline orchestrator, allowing users to develop ReAct agents that utilize iterative reasoning and external tool execution to solve complex tasks. The project distinguishes itself through a prompt optimization system that uses textual gradient descent to automatically refine prompt templates and few-shot examples. It treats model feedback as a differentiable signal, enabling a form of LLM backpropagation to iteratively improve output
Converts raw chat completion streams into a standardized format for consistent event handling.