unstract
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
- 7.5k
- Python
- AGPL-3.0
- 8 h ago
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Extract structured data and insights from documents using LLMs and decision models
本地监控 + AI 视觉 — LAN-based smartphone-powered AI monitoring framework with structured event output for data acquisition and analysis.
Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.
A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents and multi-agent swarms: durable execution, long-term memory, hybrid RAG, MCP client/server, A2A, human-in-the-loop approvals, CodeAct sandboxes, realtime voice. One streaming API, 29 providers: Claude, GPT, Gemini, Grok, DeepSeek, Ollama. Node, Bun, Deno, edge.
Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek, Ollama and more), automatic failover, Pydantic-validated structured output, embeddings with vector search, and an AI-powered router. pip install simplerllm
Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
Simplifies the retrieval, extraction, and training of structured data from various unstructured sources.
Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news aggregation, entity profiles, conflict detection, document analysis. No API keys. No in-server LLM. Structured outputs for agent chaining.
Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.
Jev / TypeSafe System One 中文精选列表:官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测,附中文上手指南,每日自动收录 GitHub 热门项目。
Schema-first structured extraction from LLMs — validated JSON from one call or a 150-page document.
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks
Generate conversational, tool-calling, structured-output, and preference datasets — easily and at scale
Browser engine for agents. HTML in, structured Semantic Object Model out. Native MCP and AWP with a supported CDP subset. Apache-2.0.
Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails the rules, and gate CI on regressions — all as one contract object per step.
ComfyUI node for local LLMs and vision models via LM Studio: prompt enhancing, image captioning, reasoning extraction, structured JSON output and VRAM management.
Make forms easier, LLM tools safer. Natural-language quantities, units, dates & ranges parsed into canonical values — zero dependencies, two-way.
Prompture is an API-first library for requesting structured JSON output from LLMs (or any structure), validating it against a schema, and running comparative tests between models.
Free ebook: Prompt Engineering for .NET Developers. Build AI apps in C# and .NET 10 with Microsoft.Extensions.AI, OpenAI, Azure AI Foundry and local LLMs in LM Studio, with runnable code and unit tests for every chapter. No Python.
One Rust API for 30+ AI providers — chat, tool calls, structured output, embeddings, reranking and media generation behind a single provider:model string, with built-in cost tracking
Curated Jev and System One papers, models, datasets, benchmarks and SDKs, with versioned sources and transparent verification levels. English / 中文.
Evidence-backed use cases, patterns, prompts, and starter code for TypeSafe Jev — a System One model for fast, typed, confidence-aware decisions in software.
Unofficial skill for building with decision models (Jev, Clef, pplx-decider, ai_decide, Ollama): typed decisions, calibrated confidence, provider differences, and prior art sorted by implementation shape.
Build Rust CLIs that AI agents can discover, call, and learn from. No MCP server needed.
C# .NET 10 sample for GPT-6 Astra on Microsoft Foundry with the Responses API, Microsoft.Extensions.AI and Entra ID: tool-based bug investigation, structured JSON BI insights, templated reports, human-approved updates and a two-document investment summary
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.
Local multimodal decisions on your Mac. Jev-compatible typed probabilities with Qwen, llama.cpp and Metal.
A sample application to demonstrate how to use Structured Outputs in OpenAI Chat Completions API with streaming, built using Next.js.
C# .NET 10 sample for GPT-6.1 Sol in Microsoft Foundry with Microsoft.Extensions.AI and the Responses API: PR triage, an approval-gated tool call, an evidence-bound vendor review, and a reasoning-effort cost comparison. Entra ID sign-in, no API key.
OpenAI-compatible Python SDK examples — chat completions, embeddings, streaming, retries, and multi-provider base_url switching. Works with XiDao, OpenRouter, Together, and any OpenAI-compatible API.
psi-fusion-insights extracts structured data from PsiQuantum fusion tech texts, summarizing techniques, benefits, challenges, and uses.
LLM data labelling — 96% accuracy, $0.26/run
Runs in the browser on Hugging Face
Get structured JSON responses from LLM using Docker
Runs in the browser on Hugging Face