YanSte / NLP

Summary of NLP

NLP Resources

Base NLP Techniques

• Base Stemming and Lemmatization
• Base Stemming Lemmatization Classification
• Base TF-IDF Similarity
• Base Neural Word Embeddings

Vector / Semantic / Embeddings

Weaviate

• Weaviate VectorDB
• Weaviate Nearest Neighbors
• Weaviate CRUD Search
• Weaviate Sparse Dense Hybrid Search
• Weaviate Multilingual Search
• Weaviate Search
• Weaviate Dense Retrieval
• Weaviate ReRank

Pinecone

• Pinecone VectorDB Search

ChromaDB

• ChromaDB Embedding Search

FAISS

• FAISS Embedding Search

Cohere

• Cohere Embeddings Search

Semantic

• Semantic Router Semantic Search
• Semantic Generative Answers

Retrieval-Augmented Generation (RAG)

Question Answering

• RAG Langchain QA

LLamaIndex

• RAG LLamaIndex Pipeline
• RAG LLamaIndex Sentence Window Retrieval
• RAG LLamaIndex Auto Merging Retrieval
• RAG LLamaIndex Ollama Auto Merging Retrieval
• RAG Agent

Tests

• RAG LLamaIndex Triad of Metrics

Large Language Model (LLM)

Basic Applications

• Basic Applications

Mistral

• Prompting
• Model Selection
• Function Calling

Langchain

• LangChain MultStepReason 1
• LangChain ReAct MultStepReason 2

Fine-Tuning

• Fine Tuning with QLoRA How in 2024
• Fine Tuning with QLoRA T5
• Fine Tuning Trainer
• Fine Tuning PEFT LoRA
• Fine Tuning POO

Fine-Tuning Options

• Fine Tuning DeepSpeed

Log Monitor Text Metrics

• Society Bias Toxicity
• Log Monitor Text Metrics with LangKit

LLMOps

• LLMOps Pipeline Dev Stag Prod