Fosowl/agenticSeek
AgenticSeek is a fully local, autonomous AI assistant powered by Deepseek R1 agents that can code, browse the web, and manage files without relying on cloud services, ensuring user data privacy and eliminating ongoing costs.
Awesome AI Agents › Programming Languages
pengfeng/ask.py
Ask.py is a simple yet powerful Python program designed to implement the search-extract-summarize flow, similar to AI search engines like Perplexity. It enables users to perform web searches, extract relevant information, and summarize the results using large language models (LLMs). The program supports running with local inference and embedding models such as Ollama, or through various API providers including OpenAI and DeepSeek. It can be operated via command line or through a Gradio UI, making it versatile for different user preferences. The core functionality involves searching the web or local files, crawling and scraping text content from the results, chunking the text into manageable pieces, and saving these chunks into a vector database. A hybrid search combining vector search and BM25 full-text search is then performed to find the most relevant chunks. Optionally, a reranker can reorder these chunks before they are used as context for an LLM to generate a summarized answer with references. Users can customize the search and output behavior extensively. For example, they can restrict searches by date or specific websites, specify output language and length, or provide a list of URLs to scrape directly. The program also supports extracting structured data using Pydantic schemas and can be automated in scripts or cron jobs for complex data extraction tasks. Ask.py serves as an educational tool to illustrate the basic concepts of AI-powered search engines and provides a playground for experimenting with different components of the search and summarization pipeline. While it is not designed for high performance or scalability, it offers a clear and configurable framework for understanding and building AI search workflows. The project also points to a more advanced open-source toolset, LeetTools, for users seeking a full-featured solution. Keywords: search-extract-summarize, AI search engine, Python, LLM, Ollama, OpenAI, DeepSeek, vector search, BM25, hybrid search, web scraping, text chunking, vector database, reranker, Pydantic, structured data extraction, Gradio UI, command line tool, automation, local files, API integration, date-restrict, target-site, output customization, AI workflow, educational tool, LeetTools.
https://github.com/pengfeng/ask.py
Also in Programming Languages
MODSetter/SurfSense
SurfSense is a highly customizable AI research agent that integrates with personal knowledge bases and external sources to provide advanced, privacy-conscious research and knowledge management capabilities.
HKUDS/AI-Researcher
AI-Researcher is a fully automated scientific discovery platform powered by large language models that autonomously conducts research from idea generation to manuscript creation.
InternLM/xtuner
XTuner is a comprehensive and efficient toolkit for fine-tuning large language and vision-language models, supporting a wide range of models and training algorithms with scalability and flexibility.
developersdigest/llm-answer-engine
A Perplexity-inspired answer engine built with Next.js and multiple AI and search technologies to provide rich, context-aware responses including sources, images, videos, and follow-up questions.
run-llama/LlamaIndexTS
LlamaIndexTS is a lightweight, extensible data framework designed to integrate large language models into server-side JavaScript applications, supporting multiple runtimes and a wide range of LLM providers.
EgoAlpha/prompt-in-context-learning
An open-source comprehensive resource and engineering guide for mastering in-context learning and prompt engineering with large language models like ChatGPT, GPT-3, and FlanT5.
AnotiaWang/deep-research-web-ui
Deep Research Web UI is a secure, AI-powered web interface that enables iterative, deep research by combining search engines, web scraping, and large language models with real-time feedback and exportable research reports.