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.
☆27Updated last year
Alternatives and similar repositories for fastassert:
Users that are interested in fastassert are comparing it to the libraries listed below
- A seamless matchmaking application that is programmed with Cohere Command R+, Stanford NLP DSPy framework, Weaviate Vector store and Crew…☆59Updated 11 months ago
- Python SDK for experimenting, testing, evaluating & monitoring LLM-powered applications - Parea AI (YC S23)☆77Updated last month
- Develop, evaluate and monitor LLM applications at scale☆100Updated 4 months ago
- OpenAI GPT hosted Agent Framework for Windows and MacOS☆36Updated 8 months ago
- Extract valuable information from your project github Stars & Forks such as email, company, twitter and then explore it with streamlit🌟☆21Updated last year
- AI real estate agent☆34Updated last year
- finance agent + with generative ui☆96Updated last year
- Use dynamic few-shot selection to tweet in a particular style☆27Updated 6 months ago
- ☆44Updated 9 months ago
- ☆53Updated 5 months ago
- Zep: Long-Term Memory for AI Assistants (Python Client)☆99Updated last week
- A Python package to dynamically load functions for OpenAI Assistant☆54Updated last year
- Routing on Random Forest (RoRF)☆136Updated 6 months ago
- Code interpreter support for o1☆32Updated 6 months ago
- Not Diamond Python SDK☆67Updated this week
- Annoucing Instructor Cloud☆34Updated 7 months ago
- Data Questionnaire Agent Chatbot☆64Updated this week
- Bridge ChatGPT with your system☆27Updated 9 months ago
- Starter app for creating an AI task completion agent with gmail capabilities.☆27Updated 9 months ago
- Build reliable, secure, and production-ready AI apps easily.☆70Updated this week
- Private ChatGPT/Perplexity. Securely unlocks knowledge from confidential business information.☆62Updated 5 months ago
- ☆17Updated 11 months ago
- auto fine tune of models with synthetic data☆75Updated last year
- Multi-Agents using Workflows☆47Updated 2 months ago
- ☆38Updated last year
- A comprehensive tool for assessing AI Agents performance in simulated poker environments☆18Updated 4 months ago
- The #1 open-source SWE-bench Verified implementation☆54Updated this week
- This repository is a combination of llama workflows and agents together which is a powerful concept.☆17Updated 7 months ago
- Anthropic Computer Use with Modal Sandboxes☆31Updated 5 months ago
- A couple scripts to grab stats from email☆42Updated 6 months ago