Канал: llmware

Local Ask and Answer Dueling Bots with Small Language Models

Local Ask and Answer Dueling Bots with Small Language Models

Use Local Chatbots for Fast Retrieval - Feat. Jina AI Re-Ranker

Use Local Chatbots for Fast Retrieval - Feat. Jina AI Re-Ranker

Multi-Model Bot for Business Docs Using Small Models

Multi-Model Bot for Business Docs Using Small Models

Advanced Techniques for Working with Different Document Types in RAG

Advanced Techniques for Working with Different Document Types in RAG

Build your Agent Inference Server with AWS for LLMWare

Build your Agent Inference Server with AWS for LLMWare

Use Agent Models to Perform Multiple Step Extraction (A SLIMs Example)

Use Agent Models to Perform Multiple Step Extraction (A SLIMs Example)

Create Phi-3 Chatbot with 20 lines of code (runs without wifi)

Create Phi-3 Chatbot with 20 lines of code (runs without wifi)

Document Summaries with Small Language Models (SLIMs Cookbook)

Document Summaries with Small Language Models (SLIMs Cookbook)

BLING PHI-3: Game Changing Model that Broke our Test! 😅

BLING PHI-3: Game Changing Model that Broke our Test! 😅

Voice Transcription with CPU Friendly AI Models Example (Greatest Speeches of 20th Century)

Voice Transcription with CPU Friendly AI Models Example (Greatest Speeches of 20th Century)

Voice to Text Transcription with CPU-Friendly AI (Whisper CPP)

Voice to Text Transcription with CPU-Friendly AI (Whisper CPP)

The Hardest Problem in RAG - what to do with NOT FOUND answers

The Hardest Problem in RAG - what to do with NOT FOUND answers

Combine Small Language Models and Web Services to Automate Financial Research (SLIMs Example)

Combine Small Language Models and Web Services to Automate Financial Research (SLIMs Example)

Generate Summaries with Topic Focus using CPU-friendly Model SLIM

Generate Summaries with Topic Focus using CPU-friendly Model SLIM

Get Yes/No Answers from Text using Small Language Model (SLIM Boolean, CPU-friendly)

Get Yes/No Answers from Text using Small Language Model (SLIM Boolean, CPU-friendly)

Sentiment Analysis and NER in 1 CPU-Friendly Model with LLMWare

Sentiment Analysis and NER in 1 CPU-Friendly Model with LLMWare

Extract custom information using SLIM Extract function calling model (Earnings Release Ex.)

Extract custom information using SLIM Extract function calling model (Earnings Release Ex.)

Natural Language Queries for SQL using SLIM (Full End-to-End Example)

Natural Language Queries for SQL using SLIM (Full End-to-End Example)

Generate Consistent LLM Output - Are we all prompting WRONG??? (Part 2)

Generate Consistent LLM Output - Are we all prompting WRONG??? (Part 2)

Generate Consistent LLM Output - Are we all prompting wrong??? (Part 1)

Generate Consistent LLM Output - Are we all prompting wrong??? (Part 1)

Text to SQL Queries with CPU Friendly AI Agents Part 2 of 2

Text to SQL Queries with CPU Friendly AI Agents Part 2 of 2

Text to SQL Queries with CPU-friendly AI Agents Part 1 of 2

Text to SQL Queries with CPU-friendly AI Agents Part 1 of 2

Generate Custom Prompts for Perfect AI Images - LLMWare Community Edition feat. Prompt Quill

Generate Custom Prompts for Perfect AI Images - LLMWare Community Edition feat. Prompt Quill

RAG with Multi-Step, Hybrid Query (Ex. 6): Fast Start to RAG (2024)

RAG with Multi-Step, Hybrid Query (Ex. 6): Fast Start to RAG (2024)

RAG with Natural Language (Semantic) Query (Ex. 5): Fast Start to RAG (2024)

RAG with Natural Language (Semantic) Query (Ex. 5): Fast Start to RAG (2024)

RAG with Text Query (Ex. 4): Fast Start to RAG

RAG with Text Query (Ex. 4): Fast Start to RAG

Prompt Models (Ex. 3): Fast Start to RAG (2024)

Prompt Models (Ex. 3): Fast Start to RAG (2024)

Build Embeddings (Ex. 2): Fast Start to RAG (2024)

Build Embeddings (Ex. 2): Fast Start to RAG (2024)

Parsing, Text Chunking and Indexing (Ex. 1): Fast Start to RAG (2024 update)

Parsing, Text Chunking and Indexing (Ex. 1): Fast Start to RAG (2024 update)

Fast Start to RAG (updated for 2024) – Intro

Fast Start to RAG (updated for 2024) – Intro

Extract Names then Query in Knowledge Base with LLMWare

Extract Names then Query in Knowledge Base with LLMWare

Auto-Generate Topics, Tags and NER using CPU-Friendly models for complex documents (SLIMs Cookbook)

Auto-Generate Topics, Tags and NER using CPU-Friendly models for complex documents (SLIMs Cookbook)

Sentiment Analysis using CPU-friendly SLIMs with LLMWare (SLIMS Cookbook using Sentiment Analysis)

Sentiment Analysis using CPU-friendly SLIMs with LLMWare (SLIMS Cookbook using Sentiment Analysis)

Create Complex Research Analysis with AI Agents using SLIM models on CPU with LLMWare

Create Complex Research Analysis with AI Agents using SLIM models on CPU with LLMWare

AI Agents with Small CPU-based LLMs with LLMWare (step by step)

AI Agents with Small CPU-based LLMs with LLMWare (step by step)

Unlock AI Agents, Function Calls and Multi-Step RAG with LLMWare

Unlock AI Agents, Function Calls and Multi-Step RAG with LLMWare

Compare Embedding Models for Side by Side Queries Using Postgres with LLMWare

Compare Embedding Models for Side by Side Queries Using Postgres with LLMWare

LLMs with No GPUs - Use Custom GGUF Models with LLMWare

LLMs with No GPUs - Use Custom GGUF Models with LLMWare

Easy Chat Using Ollama with LLMWare

Easy Chat Using Ollama with LLMWare

Use OpenChat and LM Studio with LLMWare

Use OpenChat and LM Studio with LLMWare

Run 7B Chat Models locally on your Laptop with LLMWare

Run 7B Chat Models locally on your Laptop with LLMWare

Contract Analysis Using 6B Model on Laptop with LLMWare

Contract Analysis Using 6B Model on Laptop with LLMWare

Run GGUF Quantized 7B LLMs with no GPU on your laptop

Run GGUF Quantized 7B LLMs with no GPU on your laptop

Evaluating the Deci LM-7B with LLMWare

Evaluating the Deci LM-7B with LLMWare

Evaluate LLMs for RAG with LLMWare

Evaluate LLMs for RAG with LLMWare

Invoice Processing with LLMWare

Invoice Processing with LLMWare

Create your own 'pop up' LLM inference server with LLMWare

Create your own 'pop up' LLM inference server with LLMWare

DRAGON - 7B RAG specialized LLMS in Hugging Face by LLMWare

DRAGON - 7B RAG specialized LLMS in Hugging Face by LLMWare

Fast and Easy Deployment of Free LLMWare in AWS

Fast and Easy Deployment of Free LLMWare in AWS

Ingest PDFs at Scale for RAG with LLMWare

Ingest PDFs at Scale for RAG with LLMWare

Extract Tables from PDFs

Extract Tables from PDFs

Do You Need OpenAI for RAG?

Do You Need OpenAI for RAG?

LLMWare Top 3 Strategies

LLMWare Top 3 Strategies

Use Local/No-GPU LLMs for RAG for Contract Analysis (feat. LLMWare)

Use Local/No-GPU LLMs for RAG for Contract Analysis (feat. LLMWare)

RAG using CPU-based (No-GPU required) Hugging Face Models with LLMWare on your laptop

RAG using CPU-based (No-GPU required) Hugging Face Models with LLMWare on your laptop

Fast Start to Using Retrieval Augmented Generation (RAG) with MongoDB Atlas with LLMWare

Fast Start to Using Retrieval Augmented Generation (RAG) with MongoDB Atlas with LLMWare

Fast Start to RAG with LLMWare Open Source Library (2023)

Fast Start to RAG with LLMWare Open Source Library (2023)

Use Retrieval Augmented Generation (RAG) without a Database with LLMWare

Use Retrieval Augmented Generation (RAG) without a Database with LLMWare