| { |
| "entities": { |
| "text_c-ec4611a61b53": { |
| "id": "text_c-ec4611a61b53", |
| "name": "Retrieval-Augmented Generation (RAG) is a techniqu…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "Retrieval-Augmented Generation (RAG) is a technique that enhances Large Language Models by retrieving relevant documents from a knowledge base before generating answers. RAG was introduced by Lewis et al. in 2020 and has become a standard approach for grounding LLM outputs in external knowledge. The key advantage of RAG is that it significantly reduces hallucinations by providing the model with verified source material.", |
| "_item_text": "Retrieval-Augmented Generation (RAG) is a technique that enhances Large Language Models by retrieving relevant documents from a knowledge base before generating answers. RAG was introduced by Lewis et al. in 2020 and has become a standard approach for grounding LLM outputs in external knowledge. The key advantage of RAG is that it significantly reduces hallucinations by providing the model with verified source material.", |
| "_item_page_idx": 0 |
| }, |
| "doc-4c5673cd0cc9": { |
| "id": "doc-4c5673cd0cc9", |
| "name": "rag_intro.txt", |
| "type": "document", |
| "properties": { |
| "doc_id": "b72c4759-f6b6-45fb-a01b-cb086ba472dd" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-55153b8f9577": { |
| "id": "text_c-55153b8f9577", |
| "name": "The RAG pipeline consists of five core components:…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "The RAG pipeline consists of five core components: 1.Document Ingestion — parsing and chunking source documents into manageable pieces.2.Embedding — converting text chunks into dense vector representations using models like text-embedding-3-small.3.Vector Storage — storing embeddings in a vector database such as Milvus, Pinecone, or ChromaDB.4.Retrieval — finding the most semantically similar documents to a user query using cosine similarity search.", |
| "_item_text": "The RAG pipeline consists of five core components: 1.Document Ingestion — parsing and chunking source documents into manageable pieces.2.Embedding — converting text chunks into dense vector representations using models like text-embedding-3-small.3.Vector Storage — storing embeddings in a vector database such as Milvus, Pinecone, or ChromaDB.4.Retrieval — finding the most semantically similar documents to a user query using cosine similarity search.", |
| "_item_page_idx": 0 |
| }, |
| "text_c-c3c3cde6071f": { |
| "id": "text_c-c3c3cde6071f", |
| "name": "5.Generation — passing retrieved context along wit…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 1 |
| }, |
| "content_type": "text", |
| "content_text": "5.Generation — passing retrieved context along with the query to an LLM to produce an accurate, cited response.", |
| "_item_text": "5.Generation — passing retrieved context along with the query to an LLM to produce an accurate, cited response.", |
| "_item_page_idx": 0 |
| }, |
| "doc-f4b87e7b51cb": { |
| "id": "doc-f4b87e7b51cb", |
| "name": "rag_components.txt", |
| "type": "document", |
| "properties": { |
| "doc_id": "cb8cc41d-4fb5-4760-902a-0a1b2f7b8ecf" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-ef467a62127a": { |
| "id": "text_c-ef467a62127a", |
| "name": "Milvus is an open-source vector database designed …", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "Milvus is an open-source vector database designed for similarity search at scale. It supports multiple index types including IVF_FLAT, HNSW, and DiskANN. Vector databases store embeddings as high-dimensional vectors and enable efficient approximate nearest neighbor (ANN) search. Key metrics include cosine similarity, Euclidean distance, and inner product.", |
| "_item_text": "Milvus is an open-source vector database designed for similarity search at scale. It supports multiple index types including IVF_FLAT, HNSW, and DiskANN. Vector databases store embeddings as high-dimensional vectors and enable efficient approximate nearest neighbor (ANN) search. Key metrics include cosine similarity, Euclidean distance, and inner product.", |
| "_item_page_idx": 0 |
| }, |
| "doc-1b2e2373a460": { |
| "id": "doc-1b2e2373a460", |
| "name": "vector_databases.txt", |
| "type": "document", |
| "properties": { |
| "doc_id": "1d971110-0404-499a-a3fd-902221b95293" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-7bd94cd4393c": { |
| "id": "text_c-7bd94cd4393c", |
| "name": "Text embedding models convert natural language int…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "Text embedding models convert natural language into fixed-length vector representations. OpenAI's text-embedding-3-small produces 1536-dimensional vectors optimized for semantic search. Alternative models include BGE from BAAI, E5 from Microsoft, and multilingual models for cross-lingual retrieval. Embedding quality directly impacts RAG retrieval accuracy.", |
| "_item_text": "Text embedding models convert natural language into fixed-length vector representations. OpenAI's text-embedding-3-small produces 1536-dimensional vectors optimized for semantic search. Alternative models include BGE from BAAI, E5 from Microsoft, and multilingual models for cross-lingual retrieval. Embedding quality directly impacts RAG retrieval accuracy.", |
| "_item_page_idx": 0 |
| }, |
| "doc-a97956d2e621": { |
| "id": "doc-a97956d2e621", |
| "name": "embedding_models.txt", |
| "type": "document", |
| "properties": { |
| "doc_id": "898fbb98-1b40-4229-99c2-542a8f400d47" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-676838941010": { |
| "id": "text_c-676838941010", |
| "name": "The ReAct (Reasoning + Acting) framework enables A…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "The ReAct (Reasoning + Acting) framework enables AI agents to interleave reasoning steps with tool-calling actions. ReAct agents follow a Think → Act → Observe loop, where each iteration involves the agent reasoning about what to do next, selecting and invoking a tool, and observing the result. This pattern is fundamental to building reliable AI agents.", |
| "_item_text": "The ReAct (Reasoning + Acting) framework enables AI agents to interleave reasoning steps with tool-calling actions. ReAct agents follow a Think → Act → Observe loop, where each iteration involves the agent reasoning about what to do next, selecting and invoking a tool, and observing the result. This pattern is fundamental to building reliable AI agents.", |
| "_item_page_idx": 0 |
| }, |
| "doc-19e2c95f250b": { |
| "id": "doc-19e2c95f250b", |
| "name": "react_agent.txt", |
| "type": "document", |
| "properties": { |
| "doc_id": "bbbe6cb6-d79b-4d8f-9629-d3579d4c4239" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-1926476d68ac": { |
| "id": "text_c-1926476d68ac", |
| "name": "RAG System Architecture Diagram — showing the flow…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "RAG System Architecture Diagram — showing the flow from user query to final answer.", |
| "_item_text": "RAG System Architecture Diagram — showing the flow from user query to final answer.", |
| "_item_page_idx": 0 |
| }, |
| "image-d107b040969f": { |
| "id": "image-d107b040969f", |
| "name": "image_1", |
| "type": "image", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "image", |
| "has_caption": false, |
| "index": 1 |
| }, |
| "content_type": "image", |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "doc-621766721b8c": { |
| "id": "doc-621766721b8c", |
| "name": "rag_architecture_diagram", |
| "type": "document", |
| "properties": { |
| "doc_id": "86e6838c-1570-45d1-9531-60f8048e5c13" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-723213cefe2f": { |
| "id": "text_c-723213cefe2f", |
| "name": "RAG performance benchmarks across different config…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "RAG performance benchmarks across different configurations.", |
| "_item_text": "RAG performance benchmarks across different configurations.", |
| "_item_page_idx": 0 |
| }, |
| "table-31e9e6015b3d": { |
| "id": "table-31e9e6015b3d", |
| "name": "| Configuration | Accuracy | Latency |\n| Naive RAG", |
| "type": "table", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "table", |
| "has_caption": true, |
| "index": 1 |
| }, |
| "content_type": "table", |
| "content_text": "| Configuration | Accuracy | Latency |\n| Naive RAG | 78% | 200ms |\n| Hybrid RAG | 94% | 350ms |\n| Graph RAG | 96% | 600ms |\n\n[Table]: RAG Performance Comparison\n| Configuration | Accuracy | Latency |\n| Naive RAG | 78% | 200ms |\n| Hybrid RAG | 94% | 350ms |\n| Graph RAG | 96% | 600ms |", |
| "_item_text": "| Configuration | Accuracy | Latency |\n| Naive RAG | 78% | 200ms |\n| Hybrid RAG | 94% | 350ms |\n| Graph RAG | 96% | 600ms |", |
| "_item_page_idx": 0 |
| }, |
| "doc-63f5b9638e1c": { |
| "id": "doc-63f5b9638e1c", |
| "name": "performance_benchmark", |
| "type": "document", |
| "properties": { |
| "doc_id": "b6908504-9061-41b7-bda6-da3819cdf256" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-c531165a9bda": { |
| "id": "text_c-c531165a9bda", |
| "name": "HyDE (Hypothetical Document Embeddings) improves r…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "HyDE (Hypothetical Document Embeddings) improves retrieval by generating a hypothetical answer first.", |
| "_item_text": "HyDE (Hypothetical Document Embeddings) improves retrieval by generating a hypothetical answer first.", |
| "_item_page_idx": 0 |
| }, |
| "doc-16aa639a33f8": { |
| "id": "doc-16aa639a33f8", |
| "name": "test_hyde", |
| "type": "document", |
| "properties": { |
| "doc_id": "be3bc86f-6a10-431c-9c31-71666b2feb23" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "text_c-9a5155983e92": { |
| "id": "text_c-9a5155983e92", |
| "name": "CLIP model bridges vision and language for cross-m…", |
| "type": "text_chunk", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "text", |
| "has_caption": false, |
| "index": 0 |
| }, |
| "content_type": "text", |
| "content_text": "CLIP model bridges vision and language for cross-modal retrieval.", |
| "_item_text": "CLIP model bridges vision and language for cross-modal retrieval.", |
| "_item_page_idx": 0 |
| }, |
| "image-dfc8f45882f2": { |
| "id": "image-dfc8f45882f2", |
| "name": "image_1", |
| "type": "image", |
| "properties": { |
| "page_idx": 0, |
| "content_type": "image", |
| "has_caption": false, |
| "index": 1 |
| }, |
| "content_type": "image", |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| }, |
| "doc-4d768d8694fc": { |
| "id": "doc-4d768d8694fc", |
| "name": "api_multimodal", |
| "type": "document", |
| "properties": { |
| "doc_id": "24101de9-b27a-4b1a-a63f-96aa92329107" |
| }, |
| "content_type": null, |
| "content_text": "", |
| "_item_text": "", |
| "_item_page_idx": 0 |
| } |
| }, |
| "relations": [ |
| { |
| "source": "text_c-ec4611a61b53", |
| "target": "doc-4c5673cd0cc9", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-55153b8f9577", |
| "target": "doc-f4b87e7b51cb", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-c3c3cde6071f", |
| "target": "doc-f4b87e7b51cb", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-55153b8f9577", |
| "target": "text_c-c3c3cde6071f", |
| "type": "nearby", |
| "weight": 0.8 |
| }, |
| { |
| "source": "text_c-ef467a62127a", |
| "target": "doc-1b2e2373a460", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-7bd94cd4393c", |
| "target": "doc-a97956d2e621", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-676838941010", |
| "target": "doc-19e2c95f250b", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-1926476d68ac", |
| "target": "doc-621766721b8c", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "image-d107b040969f", |
| "target": "doc-621766721b8c", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-1926476d68ac", |
| "target": "image-d107b040969f", |
| "type": "nearby", |
| "weight": 0.8 |
| }, |
| { |
| "source": "image-d107b040969f", |
| "target": "text_c-1926476d68ac", |
| "type": "describes", |
| "weight": 0.6 |
| }, |
| { |
| "source": "text_c-723213cefe2f", |
| "target": "doc-63f5b9638e1c", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "table-31e9e6015b3d", |
| "target": "doc-63f5b9638e1c", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-723213cefe2f", |
| "target": "table-31e9e6015b3d", |
| "type": "nearby", |
| "weight": 0.8 |
| }, |
| { |
| "source": "table-31e9e6015b3d", |
| "target": "text_c-723213cefe2f", |
| "type": "describes", |
| "weight": 0.6 |
| }, |
| { |
| "source": "text_c-c531165a9bda", |
| "target": "doc-16aa639a33f8", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-9a5155983e92", |
| "target": "doc-4d768d8694fc", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "image-dfc8f45882f2", |
| "target": "doc-4d768d8694fc", |
| "type": "belongs_to", |
| "weight": 1.0 |
| }, |
| { |
| "source": "text_c-9a5155983e92", |
| "target": "image-dfc8f45882f2", |
| "type": "nearby", |
| "weight": 0.8 |
| }, |
| { |
| "source": "image-dfc8f45882f2", |
| "target": "text_c-9a5155983e92", |
| "type": "describes", |
| "weight": 0.6 |
| } |
| ] |
| } |
