phospho-app / fastassert
Dockerized LLM inference server with constrained output (JSON mode), built on top of vLLM and outlines. Faster, cheaper and without rate limits. Compare the quality and latency to your current LLM API provider.
☆28Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for fastassert
- AI real estate agent☆31Updated 9 months ago
- Code interpreter support for o1☆30Updated 2 months ago
- A seamless matchmaking application that is programmed with Cohere Command R+, Stanford NLP DSPy framework, Weaviate Vector store and Crew…☆57Updated 6 months ago
- Crawl and convert any website into clean markdown☆41Updated 5 months ago
- Bridge ChatGPT with your system☆26Updated 4 months ago
- ☆24Updated 5 months ago
- 🤖 Headless IDE for AI agents☆129Updated this week
- API playground for Deepgram built with Streamlit☆20Updated 6 months ago
- Your local personalised AI agent☆40Updated 3 weeks ago
- ☆38Updated 3 weeks ago
- Open source AI analyst powered by E2B. Analyze your CSV files with Llama 3.1 and create interactive charts.☆31Updated last week
- Develop, evaluate and monitor LLM applications at scale☆93Updated this week
- Annoucing Instructor Cloud☆34Updated 2 months ago
- Open-source RAG evaluation through users' feedback☆160Updated 6 months ago
- LlamaWorksDB is a Retrieval Augmented Generation (RAG) product designed to interact with the documentation of various products such as Ll…☆15Updated 6 months ago
- Dynamic Metadata based RAG Framework☆71Updated 3 months ago
- LangChain chat model abstractions for dynamic failover, load balancing, chaos engineering, and more!☆79Updated 9 months ago
- sample app about authz and AI☆27Updated this week
- ☆43Updated 5 months ago
- ☆61Updated 3 weeks ago
- ☆45Updated 6 months ago
- Data Questionnaire Agent Chatbot☆61Updated 3 weeks ago
- A simple Python sandbox for helpful LLM data agents☆162Updated 4 months ago
- A Python package to dynamically load functions for OpenAI Assistant☆55Updated 11 months ago
- Generate Tools and Toolkits from any Python SDK -- no extra code required☆50Updated last week
- A RAG powered web search with Tavily, LangChain, Mistral AI ( leveraging groq LPU) . The full stack web app build in Databutton.☆29Updated 8 months ago
- ⚡️ Perplexity.ai style LLM response streaming☆139Updated 6 months ago
- ☆44Updated 3 weeks ago
- LangEvals aggregates various language model evaluators into a single platform, providing a standard interface for a multitude of scores a…☆40Updated this week
- An awesome & curated list of best LLMOps tools for developers☆23Updated last year