Progressive Distillation

David Mezzetti for NeuML Posted on May 31 • Originally published at neuml.hashnode.dev           Progressive Distillation # ai # llm # rag # vectordatabase Tutorial Series for txtai (85 Part Series) 1 Tutorial series on txtai 2 Build an Embeddings index with Hugging Face Datasets ... 81 more parts... 3 Build an Embeddings index from a data source 4 Add semantic search to Elasticsearch 5 Extractive QA with txtai 6 Extractive QA with Elasticsearch 7 Apply labels with zero-shot classification 8 txtai API Gallery 9 Building abstractive text summaries 10 Extract text from documents 11 Transcribe audio to text 12 Translate text between languages 13 Similarity search with images 14 Run pipeline workflows 15 Distributed embeddings cluster 16 Train a text labeler 17 Train without labels 18 Export and run models with ONNX 19 Train a QA model 20 Extractive QA to build structured data 21 Export and run other machine learning models 22 Transform tabular data with composable workflows 23 Tensor workflows 24 💡 What's new in txtai 4.0 25 Generate image captions and detect objects 26 Entity extraction workflows 27 Workflow Scheduling 28 Push notifications with workflows 29 Anatomy of a txtai index 30 Embeddings SQL custom functions 31 Near duplicate image detection 32 Model explainability 33 Query translation 34 Build a QA database 35 Pictures are a worth a thousand words 36 Run txtai in native code 37 Embeddings index components 38 Introducing the Semantic Graph 39 Classic Topic Modeling with BM25 40 Text to speech generation 41 Train a language model from scratch 42 Prompt-driven search with LLMs 43 Embeddings in the Cloud 44 Prompt templates and task chains 45 Customize your own embeddings database 46 💡 What's new in txtai 6.0 47 Building an efficient sparse keyword index in Python 48 Benefits of hybrid search 49 External database integration 50 All about vector quantization 51 Custom API Endpoints 52 Build RAG pipelines with txtai 53 Integ