Open Issues Need Help
View All on GitHub Implement SectionNormalizer - assign section ids to headings about 2 hours ago
good first issue parser stale
The document normalization engine RAG has always needed. Parse any document, understand its structure, build RAG that actually works.
Python
#ai#bm25#docling#document-ai#document-intelligence#document-processing#embeddings#information-retrieval#knowledge-base#llm#nlp#open-source#python#rag#vector-search
Implement Quantizer - float16, int8, binary embedding compression about 2 hours ago
good first issue stale
The document normalization engine RAG has always needed. Parse any document, understand its structure, build RAG that actually works.
Python
#ai#bm25#docling#document-ai#document-intelligence#document-processing#embeddings#information-retrieval#knowledge-base#llm#nlp#open-source#python#rag#vector-search
Implement PDFParser using Docling about 2 months ago
good first issue parser
The document normalization engine RAG has always needed. Parse any document, understand its structure, build RAG that actually works.
Python
#ai#bm25#docling#document-ai#document-intelligence#document-processing#embeddings#information-retrieval#knowledge-base#llm#nlp#open-source#python#rag#vector-search
Add ExcelParser - preserve table structure from XLSX files about 2 months ago
good first issue parser
The document normalization engine RAG has always needed. Parse any document, understand its structure, build RAG that actually works.
Python
#ai#bm25#docling#document-ai#document-intelligence#document-processing#embeddings#information-retrieval#knowledge-base#llm#nlp#open-source#python#rag#vector-search