#146 · Primary category: LLM Application Frameworks
simpleaichat
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
Project last updated:07/03/24
GitHub Stars
3.5K
Forks
216
Contributors
12
License
MIT
Why we included this project
Talking to a GPT-class model usually means wading through SDK boilerplate, but this package keeps the whole interaction down to a few lines. It wraps ChatGPT and GPT-4 behind a clean Python interface, and still gives you the extras that matter in real apps: token-conscious workflows that lower cost and latency, concurrent chats, async calls, streaming, and tool support. The codebase is deliberately small, so you can follow exactly what happens on each request, which helps when you need predictable behavior in production. Its example notebooks, including a coding assistant that trims output for faster, cheaper generation and an async pattern that fans out many chats at once, are practical starting points for building similar features yourself.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform