StarTrail-org/PixelRAG
- Source
- GitHub
- First trending
- Category
- RAG and search
- GitHub stars
- 9,976
- Main language
- Python
This page introduces an external open-source repository. It is not an HDATF product.
What it does
PixelRAG renders web pages, PDFs and images as screenshots and runs retrieval over the images directly, so tables, charts and layout that HTML parsing drops stay intact. It is the official code for a research paper.
How it helps ATF
Retrieving over page images instead of parsed text could be worth comparing for Company Brain search over company documents that contain tables, charts and complex layouts.
License
Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.
More in this category
- semantica-agi/semantica
A Python library that ingests enterprise data, extracts key information, builds a context graph and knowledge graph, and runs graph analytics and reasoning over them. It keeps decision provenance for end-to-end traceability. - GoogleCloudPlatform/knowledge-catalog
Tools, agents and samples for Google Cloud Knowledge Catalog, formerly Dataplex, a data catalog and metadata platform that provides a knowledge graph over structured and unstructured data. The samples show context management, enrichment and retrieval for AI agents. - zvec-ai/zvec-grep
zg is a local-first search tool that combines ripgrep, BM25 and vector search behind one interface, usable from the CLI or by an agent. It searches code, documents and structured data and returns ranked results with source locations. - RyanCodrai/turbovec
A vector index written in Rust with Python bindings, built on Google Research's TurboQuant quantizer. It adds vectors without a training step, saves changes incrementally, filters by id at search time and runs fully locally. - Tencent/WeKnora
WeKnora turns raw documents into RAG-based Q&A and a ReAct agent that uses retrieval, MCP tools and sandboxes. Its Wiki Mode has agents build an interlinked, editable markdown knowledge base with revision history.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.