# KNOWLEDGE - [Vector Databases](https://training.continuumlabs.ai/knowledge/vector-databases.md) - [A Comprehensive Survey on Vector Databases](https://training.continuumlabs.ai/knowledge/vector-databases/a-comprehensive-survey-on-vector-databases.md) - [Vector database management systems: Fundamental concepts, use-cases, and current challenges](https://training.continuumlabs.ai/knowledge/vector-databases/vector-database-management-systems-fundamental-concepts-use-cases-and-current-challenges.md) - [Using the Output Embedding to Improve Language Models](https://training.continuumlabs.ai/knowledge/vector-databases/using-the-output-embedding-to-improve-language-models.md) - [Decoding Sentence-BERT](https://training.continuumlabs.ai/knowledge/vector-databases/decoding-sentence-bert.md) - [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://training.continuumlabs.ai/knowledge/vector-databases/colbert-efficient-and-effective-passage-search-via-contextualized-late-interaction-over-bert.md): The widely cited paper by Omar Khattab and Matei Zaharia from Stanford University - [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://training.continuumlabs.ai/knowledge/vector-databases/simcse-simple-contrastive-learning-of-sentence-embeddings.md) - [Questions Are All You Need to Train a Dense Passage Retriever](https://training.continuumlabs.ai/knowledge/vector-databases/questions-are-all-you-need-to-train-a-dense-passage-retriever.md) - [Improving Text Embeddings with Large Language Models](https://training.continuumlabs.ai/knowledge/vector-databases/improving-text-embeddings-with-large-language-models.md): Microsoft Corporation - [Massive Text Embedding Benchmark](https://training.continuumlabs.ai/knowledge/vector-databases/massive-text-embedding-benchmark.md): The leaderboard for embedding models - [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://training.continuumlabs.ai/knowledge/vector-databases/rocketqav2-a-joint-training-method-for-dense-passage-retrieval-and-passage-re-ranking.md) - [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://training.continuumlabs.ai/knowledge/vector-databases/llm2vec-large-language-models-are-secretly-powerful-text-encoders.md) - [Embedding and Fine-Tuning in Neural Language Models](https://training.continuumlabs.ai/knowledge/vector-databases/embedding-and-fine-tuning-in-neural-language-models.md): Mathematical representations of text - [Embedding Model Construction](https://training.continuumlabs.ai/knowledge/vector-databases/embedding-model-construction.md) - [Demystifying Embedding Spaces using Large Language Models](https://training.continuumlabs.ai/knowledge/vector-databases/demystifying-embedding-spaces-using-large-language-models.md): Guy Tennenholtz et al. from Google Research - [Fine-Tuning Llama for Multi-Stage Text Retrieval](https://training.continuumlabs.ai/knowledge/vector-databases/fine-tuning-llama-for-multi-stage-text-retrieval.md): Microsoft Research - [Large Language Model Based Text Augmentation Enhanced Personality Detection Model](https://training.continuumlabs.ai/knowledge/vector-databases/large-language-model-based-text-augmentation-enhanced-personality-detection-model.md) - [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://training.continuumlabs.ai/knowledge/vector-databases/one-embedder-any-task-instruction-finetuned-text-embeddings.md) - [Vector Databases are not the only solution](https://training.continuumlabs.ai/knowledge/vector-databases/vector-databases-are-not-the-only-solution.md): Yingjun Wu - [Knowledge Graphs](https://training.continuumlabs.ai/knowledge/vector-databases/knowledge-graphs.md): Analysis of Knowledge Graphs and Influence of Generative AI and LLMs - [Harnessing Knowledge Graphs to Elevate AI: A Technical Exploration](https://training.continuumlabs.ai/knowledge/vector-databases/knowledge-graphs/harnessing-knowledge-graphs-to-elevate-ai-a-technical-exploration.md): Finally a semantic data architecture - [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://training.continuumlabs.ai/knowledge/vector-databases/knowledge-graphs/unifying-large-language-models-and-knowledge-graphs-a-roadmap.md) - [Approximate Nearest Neighbor (ANN)](https://training.continuumlabs.ai/knowledge/vector-databases/approximate-nearest-neighbor-ann.md) - [High Dimensional Data](https://training.continuumlabs.ai/knowledge/vector-databases/high-dimensional-data.md) - [Principal Component Analysis (PCA)](https://training.continuumlabs.ai/knowledge/vector-databases/principal-component-analysis-pca.md) - [Vector Similarity Search - HNSW](https://training.continuumlabs.ai/knowledge/vector-databases/vector-similarity-search-hnsw.md) - [FAISS (Facebook AI Similarity Search)](https://training.continuumlabs.ai/knowledge/vector-databases/faiss-facebook-ai-similarity-search.md) - [Unsupervised Dense Retrievers](https://training.continuumlabs.ai/knowledge/vector-databases/unsupervised-dense-retrievers.md) - [Retrieval Augmented Generation](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation.md): A critical piece of the generative AI infrastructure - [Retrieval-Augmented Generation for Large Language Models: A Survey](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/retrieval-augmented-generation-for-large-language-models-a-survey.md) - [Fine-Tuning or Retrieval?](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/fine-tuning-or-retrieval.md): Microsoft, Israel - [Revolutionising Information Retrieval: The Power of RAG in Language Models](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/revolutionising-information-retrieval-the-power-of-rag-in-language-models.md) - [A Survey on Retrieval-Augmented Text Generation](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/a-survey-on-retrieval-augmented-text-generation.md): Huayang Li, Yixuan Su, Deng Cai, Yan Wang, Lemao Liu - [REALM: Retrieval-Augmented Language Model Pre-Training](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/realm-retrieval-augmented-language-model-pre-training.md): Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, Ming-Wei Chang - [Retrieve Anything To Augment Large Language Models](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/retrieve-anything-to-augment-large-language-models.md) - [Generate Rather Than Retrieve: Large Language Models Are Strong Context Generators](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/generate-rather-than-retrieve-large-language-models-are-strong-context-generators.md) - [Active Retrieval Augmented Generation](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/active-retrieval-augmented-generation.md): FLARE! - [DSPy: LM Assertions: Enhancing Language Model Pipelines with Computational Constraints](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/dspy-lm-assertions-enhancing-language-model-pipelines-with-computational-constraints.md) - [DSPy: Compiling Declarative Language Model Calls](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/dspy-compiling-declarative-language-model-calls.md) - [DSPy: In-Context Learning for Extreme Multi-Label Classification](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/dspy-in-context-learning-for-extreme-multi-label-classification.md) - [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/optimizing-instructions-and-demonstrations-for-multi-stage-language-model-programs.md) - [HYDE: Revolutionising Search with Hypothetical Document Embeddings](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/hyde-revolutionising-search-with-hypothetical-document-embeddings.md) - [Enhancing Recommender Systems with Large Language Model Reasoning Graphs](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/enhancing-recommender-systems-with-large-language-model-reasoning-graphs.md) - [Retrieval Augmented Generation (RAG) versus fine tuning](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/retrieval-augmented-generation-rag-versus-fine-tuning.md) - [RAFT: Adapting Language Model to Domain Specific RAG](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/raft-adapting-language-model-to-domain-specific-rag.md) - [Summarisation Methods and RAG](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/summarisation-methods-and-rag.md) - [Lessons Learned on LLM RAG Solutions](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/lessons-learned-on-llm-rag-solutions.md): Injecting data via embedding model into your vector database for future retrieval - [Stanford: Retrieval Augmented Language Models](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/stanford-retrieval-augmented-language-models.md): Youtube Lecture - January 2024 - [Overview of RAG Approaches with Vector Databases](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/overview-of-rag-approaches-with-vector-databases.md): Some random tips on RAG and vector databases - [Mastering Chunking in Retrieval-Augmented Generation (RAG) Systems](https://training.continuumlabs.ai/knowledge/retrieval-augmented-generation/mastering-chunking-in-retrieval-augmented-generation-rag-systems.md) - [Semantic Routing](https://training.continuumlabs.ai/knowledge/semantic-routing.md) - [Resource Description Framework (RDF)](https://training.continuumlabs.ai/knowledge/resource-description-framework-rdf.md) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://training.continuumlabs.ai/knowledge.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.