跳到正文- Web Search APIs for Agents
- Vector Databases
- Text-to-SQL
- Source: Zheng et al. 2023: Step-Back Prompting
- Source: Yan et al. 2024: Corrective Retrieval Augmented Generation (CRAG)
- Source: Weaviate vector indexing, filtering and quantization docs
- Source: Weaviate docs: Hybrid search
- Source: Wang et al. 2023: Query2doc
- Source: Voyage AI text embeddings documentation
- Source: ViDoRe V3 (Loison et al., ACL 2026)
- Source: Vespa blog 2024: Scaling ColPali to billions of PDFs
- Source: Vector Databases Compared (Notebook tutorial)
- Source: Unstructured Docs on Partitioning, Elements and Hi-Res Models
- Source: Unstructured Docs on Chunking
- Source: UMBRELA: An Open-Source Reproduction of the Bing Relevance Assessor (Upadhyay et al.)
- Source: The TREC-8 Question Answering Track Report (Voorhees)
- Source: The Faiss Library (Douze et al.)
- Source: Text Embeddings by Weakly-Supervised Contrastive Pre-training (E5)
- Source: Tantivy bm25.rs (source code)
- Source: TableFormer (Nassar et al., 2022) and OTSL (Lysak et al., 2023)
- Source: Sun et al. 2023: RankGPT (Is ChatGPT Good at Search?)
- Source: Spider 2.0 (Lei et al., ICLR 2025) and Leaderboard
- Source: Spider (Yu et al., EMNLP 2018)
- Source: Snowflake Cortex Analyst Verified Query Repository Docs
- Source: Singh et al. 2025: Agentic Retrieval-Augmented Generation, a Survey
- Source: Sentence-Transformers docs: Cross-Encoders
- Source: Santhanam et al. 2022: PLAID
- Source: Santhanam et al. 2021: ColBERTv2
- Source: Robertson & Zaragoza 2009: The Probabilistic Relevance Framework: BM25 and Beyond
- Source: Ragas docs: Available metrics
- Source: Rackauckas 2024: RAG-Fusion
- Source: Qdrant tutorial: PDF Retrieval at Scale (ColPali/ColQwen)
- Source: Qdrant indexing documentation
- Source: Qdrant docs: Vectors (multivectors)
- Source: Press et al. 2022: Self-Ask (Measuring and Narrowing the Compositionality Gap)
- Source: Pinecone serverless architecture (Pinecone blog)
- Source: pgvector README
- Source: Pervasive Annotation Errors Break Text-to-SQL Benchmarks (Jin et al., 2026)
- Source: OpenSearch docs: Normalization processor
- Source: OpenSearch blog: Improving document retrieval with sparse semantic encoders
- Source: OpenAI Vector embeddings guide
- Source: On the Theoretical Limitations of Embedding-Based Retrieval (Weller et al.)
- Source: OmniDocBench (Ouyang et al., CVPR 2025) and Leaderboard
- Source: olmOCR (Poznanski et al., 2025)
- Source: Notebook: RAG vs CAG vs GraphRAG
- Source: Notebook: Driver-Licence Recognizer Lab
- Source: Notebook experiment 24: Self-RAG
- Source: Notebook experiment 23: Corrective RAG
- Source: Notebook experiment 22: Agentic RAG
- Source: Notebook experiment 14: RAG + CAG
- Source: Notebook experiment 13: RAG
- Source: MTEB: Massive Text Embedding Benchmark (Muennighoff et al.)
- Source: MMTEB: Massive Multilingual Text Embedding Benchmark (Enevoldsen et al.)
- Source: Mistral OCR Announcement
- Source: Milvus Index Explained (Milvus docs)
- Source: Microsoft Research: LazyGraphRAG
- Source: Microsoft GraphRAG documentation
- Source: Merola & Singh 2025: Late Chunking vs Contextual Retrieval
- Source: Matryoshka Representation Learning (Kusupati et al.)
- Source: Ma et al. 2023: Query Rewriting for Retrieval-Augmented LLMs
- Source: Lù 2024: BM25S
- Source: LlamaParse Tiers and Pricing Docs
- Source: LlamaIndex retrieval evaluation metrics (source code)
- Source: LlamaIndex framework documentation (RAG, indexes, query engines, agents)
- Source: Lewis et al. 2020: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Source: Large Language Models Can Accurately Predict Searcher Preferences (Thomas et al.)
- Source: LangChain SelfQueryRetriever and query constructor (langchain_classic)
- Source: LangChain MultiQueryRetriever (langchain_classic)
- Source: Khattab & Zaharia 2020: ColBERT
- Source: Kamphuis et al. 2020: Which BM25 Do You Mean?
- Source: Introduction to Information Retrieval, ch. 8: Evaluation in IR (Manning, Raghavan, Schütze)
- Source: Improving agent with semantic search (Cursor, 2025)
- Source: illuin-tech/colpali repository (ColVision models)
- Source: IBM Granite-Docling Announcement
- Source: How Embedding Models Work (Notebook tutorial)
- Source: Günther et al. 2024: Late Chunking
- Source: Gao et al. 2022: HyDE (Precise Zero-Shot Dense Retrieval without Relevance Labels)
- Source: Formal, Piwowarski & Clinchant 2021: SPLADE
- Source: Formal et al. 2021: SPLADE v2
- Source: Faiss indexes (Faiss wiki)
- Source: Es et al. 2023: RAGAS, Automated Evaluation of Retrieval Augmented Generation
- Source: Elasticsearch docs: Similarity settings
- Source: Elasticsearch docs: Reciprocal rank fusion retriever
- Source: Elastic: Practical BM25, Part 2
- Source: Efficient and robust ANN search using Hierarchical Navigable Small World graphs (Malkov & Yashunin)
- Source: Edge et al. 2024: From Local to Global, a Graph RAG Approach
- Source: dsRAG (D-Star AI) README
- Source: Docling Technical Report (Auer et al., 2024)
- Source: Docling Documentation
- Source: DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node
- Source: DIN-SQL (Pourreza and Rafiei, NeurIPS 2023)
- Source: Dhulipala et al. 2024: MUVERA
- Source: dbt Labs, Semantic Layer vs. Text-to-SQL: 2026 Benchmark Update
- Source: Cumulated Gain-Based Evaluation of IR Techniques (Järvelin and Kekäläinen)
- Source: Cormack, Clarke & Büttcher 2009: Reciprocal Rank Fusion
- Source: ColPali (Faysse et al., ICLR 2025)
- Source: Cohere embeddings documentation
- Source: Cohere docs: Rerank overview
- Source: Clavié et al. 2024: Token Pooling for Multi-Vector Retrieval
- Source: Chroma: Evaluating Chunking Strategies for Retrieval
- Source: Chroma documentation introduction
- Source: CHESS (Talaei et al., 2024)
- Source: Chen et al. 2024: BGE-M3 (M3-Embedding)
- Source: Chan et al. 2024: Don't Do RAG, Cache-Augmented Generation
- Source: C-Pack: Packed Resources for General Chinese Embeddings (BGE)
- Source: Bruch, Gai & Ingber 2022: An Analysis of Fusion Functions for Hybrid Retrieval
- Source: BIRD Benchmark (Li et al., NeurIPS 2023) and Leaderboard
- Source: Binary and Scalar Embedding Quantization (Hugging Face blog)
- Source: BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of IR Models (Thakur et al.)
- Source: Asai et al. 2023: Self-RAG
- Source: Apache Lucene BM25Similarity (javadoc and source)
- Source: Anthropic: Introducing Contextual Retrieval
- Source: Anthropic cookbook: Contextual Retrieval guide
- Retrieval-augmented generation (RAG)
- Retrieval Metrics
- Reranking
- Query Transformation
- LlamaIndex
- Late-Interaction Retrieval
- Hybrid search
- GraphRAG
- Embeddings
- Document Processing
- Contextual Retrieval
- Chunking
- BM25
- ANN Indexes
- Agentic RAG