Pinned Repositories
beam
Apache Beam is a unified programming model for Batch and Streaming
dify
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
flink
Apache Flink
flink-table-store
An Apache Flink subproject to provide storage for dynamic tables.
form-create
:fire::fire::fire: 强大的表单生成器|Form builder with dynamic rendering, data collection, validation and submission capabilities, built-in 17 common form components, support for two-way data binding, event extension, and support for building built-in components and any vue components using json.
HBoard
The most easiest to use, self-service open BI reporting and BI dashboard and BI monitor screen platform.
HBoardDoc
kyuubi
Apache Kyuubi is a distributed and multi-tenant gateway to provide serverless SQL on data warehouses and lakehouses.
langchain4j
Java version of LangChain
werewolf-agent
基于LLM的狼人杀Agent，让AI自己玩狼人杀游戏，一个java版实现的“玩具”
junjiem's Repositories
junjiem/werewolf-agent
基于LLM的狼人杀Agent，让AI自己玩狼人杀游戏，一个java版实现的“玩具”
junjiem/dify
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
junjiem/AutoStudio
AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation
junjiem/best-effort-json-parser
Parse incomplete json text in best-effort manner
junjiem/browser-use
Open-Source Web Automation library with any LLM
junjiem/dspy
DSPy: The framework for programming—not prompting—foundation models
junjiem/gateway
A Blazing Fast AI Gateway. Route to 100+ LLMs with 1 fast & friendly API.
junjiem/inference
Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.
junjiem/JavaVision
JavaVision是一个基于Java开发的全能视觉智能识别项目。该项目起源于对图像处理和人工智能领域的热情，以及对Java作为主要编程语言的坚持。在AI领域，大多数解决方案都是使用Python实现的，因此决定充分利用Java的优势来构建一个功能强大且易于集成的视觉智能识别平台。
junjiem/jsonrepair
Repair invalid JSON documents
junjiem/jvppeteer
Headless Chrome For Java （Java 爬虫）
junjiem/langchain4j-embeddings
junjiem/LangGPT
LangGPT: Empowering everyone to become a prompt expert!🚀 Structured Prompt，Language of GPT, 结构化提示词，结构化Prompt
junjiem/late-chunking
Code for explaining and evaluating late chunking (chunked pooling)
junjiem/llama_index
LlamaIndex (formerly GPT Index) is a data framework for your LLM applications
junjiem/llm_aided_ocr
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
junjiem/marker
Convert PDF to markdown quickly with high accuracy
junjiem/memary
Longterm Memory for Autonomous Agents.
junjiem/mindsdb
The platform for building AI from enterprise data
junjiem/MinerU
MinerU is a one-stop, open-source, high-quality data extraction tool，supports PDF/webpage/e-book extraction.
junjiem/quarkus-langchain4j
Quarkus Langchain4j extension
junjiem/ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
junjiem/semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
junjiem/spring-ai
An Application Framework for AI Engineering
junjiem/sqlglot
Python SQL Parser and Transpiler
junjiem/streamlit
Streamlit — A faster way to build and share data apps.
junjiem/SuperPrompt
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
junjiem/supersonic
SuperSonic is the next-generation BI platform that integrates Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.
junjiem/tabula-java
Extract tables from PDF files
junjiem/zerox
Zero shot pdf OCR with gpt-4o-mini