nlp 163 rag 132 ai 131 parsing 96 agents 88 llm 87 tools 86 orchestration-framework 84 orchestration 84 monorepo 84 modular 84 metrics 84 measures 84 llm-framework 84 factories 84 tooling 84 vectors 84 swarmauri 59 embeddings 59 pdf 40 python 39 tool 35 retrieval 34 document-processing 27 vector-database 24 ocr 24 retrieval-augmented-generation 23 langchain 22 markdown 22 semantic-search 20 document 19 jupyter 18 text-splitting 17 openai 17 text 16 vector-search 15 notebook 15 semantic-chunking 14 chunk 13 parser 13 vector 13 designed 12 extraction 12 docx 11 text-processing 11 embedding 11 rust 11 ollama 11 llamaindex 10 tree-sitter 10 evaluation 10 mcp 10 community 9 store 9 text-chunking 9 tokenization 9 vectorstore 9 claude 9 semantic 9 docling 9 natural-language-processing 8 documents 8 gemini 8 text-extraction 8 RAG 8 machine-learning 8 anthropic 7 pinecone 7 document-parsing 7 xlsx 7 html 7 text-splitter 7 information-retrieval 7 cli 6 nbconvert 6 tokens 6 example 6 ast 6 context-window 6 client 6 pptx 6 faiss 6 qdrant 6 document-intelligence 6 node 6 deduplication 6 streaming 5 artificial-intelligence 5 pipeline 5 llms 5 NLP 5 kernel 5 code-analysis 5 reranking 5 ingestion 5 context 5 chromadb 5 prompt-engineering 5 elixir 5 model-context-protocol 5