GenAI Stack (old)
v0.2.0
v0.2.0
  • Getting Started
    • ๐Ÿ’ฌIntroduction
    • ๐Ÿš€Quickstart with colab
    • ๐Ÿ“˜Default Data Types
    • ๐Ÿช›Installation
  • Components
    • โœจIntroduction
    • ๐ŸšœETL
      • ๐Ÿ”ฅQuickstart
      • ๐ŸฆœLangchain
      • ๐Ÿฆ™LLama Hub
    • ๐ŸŒฑEmbeddings
      • ๐Ÿ”ฅQuickstart
      • ๐ŸฆœLangchain
      • ๐Ÿ“–Advanced Usage
    • ๐Ÿ”ฎVector Database
      • ๐Ÿ”ฅQuickstart
      • ๐Ÿ“ฆChromadb
      • ๐Ÿ“ฆWeaviate
      • ๐Ÿ“–Advanced Usage
    • ๐Ÿ“šPrompt Engine
      • ๐Ÿ”ฅQuickstart
      • ๐Ÿ“–Advanced Usage
    • ๐Ÿ“คRetrieval
      • ๐Ÿ”ฅQuickstart
      • ๐Ÿ“–Advanced Usage
    • ๏ธ๏ธ๏ธ๐Ÿ—ƒ๏ธ LLM Cache
      • ๐Ÿ”ฅQuickstart
    • ๐Ÿ“ฆMemory
      • ๐Ÿ”ฅQuickstart
      • ๐Ÿ“–Advanced Usage
    • ๐Ÿฆ„LLMs
      • OpenAI
      • GPT4All
      • Hugging Face
      • Custom Model
  • Advanced Guide
    • ๐Ÿ’ปGenAI Stack API Server
    • ๐Ÿ”ƒGenAI Server API's Reference
  • Example Use Cases
    • ๐Ÿ’ฌChat on PDF
    • ๐Ÿ’ฌChat on CSV
    • ๐Ÿ’ฌSimilarity Search on JSON
    • ๐Ÿ“–Document Search
    • ๐Ÿ’ฌRAG pipeline
    • ๐Ÿ“šInformation Retrieval Pipeline
  • ๐Ÿง‘CONTRIBUTING.md
Powered by GitBook
On this page
  • Supported Models:
  • Custom Models
  1. Components

LLMs

Run an LLM model with few simple steps

PreviousAdvanced UsageNextOpenAI

Last updated 1 year ago

Model is the component that determines which LLM to run. This component is mainly for running LLM models under a http server and access through an API endpoint. Model is for loading the model and its necessary preprocess and postprocess functions to parse the retrieval context and the user prompt properly and give to the model for inference. The response classes can also be customized according to the modelโ€™s requirements. GenAI Stack supports things like raw Response (strings or bytes) or JsonResponse. Default is JsonResponse.

LLMStack pre-includes few models for trying out some popular models available out there.

More models will be added in the later releases. We welcome contributions if a model has to be included.

Supported Models:

Custom Models

Instructions on how to create a custom model can be found .

๐Ÿฆ„
OpenAI
GPt4All
here