LiteLLM Tutorial to Call Any LLM with API Locally

preview_player
Показать описание
This video shows how to install LiteLLM locally on Windows or Linux and call API of Anthropic, Huggingface, Cohere, TogetherAI, Azure, OpenAI, AWS, GCP, etc.

#litellm

PLEASE FOLLOW ME:

RELATED VIDEOS:

All rights reserved © 2021 Fahd Mirza
  1. Fahd Mirza
Рекомендации по теме
LiteLLM Tutorial to 0:08:34

LiteLLM Tutorial to Call Any LLM with API Locally

LiteLLM: One-Function Call 0:02:51

LiteLLM: One-Function Call to ANY Large Language Model! 🤯 UNBELIEVABLE!

Power Each AI 0:15:07

Power Each AI Agent With A Different LOCAL LLM (AutoGen + Ollama Tutorial)

LiteLLM Proxy UI 0:12:29

LiteLLM Proxy UI | Easy AI API Management & Secure Authentication

Replace OpenAI API 0:09:32

Replace OpenAI API with local models: Ollama + LiteLLM, text gen webui, google colab

LiteLLM Chatbot: Build 0:02:38

LiteLLM Chatbot: Build Your Own in MINUTES! INSANE! 🤖🔥

Function Calling in 0:08:49

Function Calling in Ollama vs OpenAI

Integrate Different LLMs 0:10:37

Integrate Different LLMs in One Code with LiteLLM

API For Open-Source 0:08:17

API For Open-Source Models 🔥 Easily Build With ANY Open-Source LLM

LangChain using LiteLLM 0:03:05

LangChain using LiteLLM

Run AutoGEN using 0:11:59

Run AutoGEN using Ollama/LiteLLM in SIMPLE Steps | Updated (Use Case)

LiteLLM with Ollama 0:09:08

LiteLLM with Ollama - Run 100+ LLMs Locally Without Changing Code

What is LiteLLM? 0:04:54

What is LiteLLM?

Introducing liteLLM Proxy 0:01:56

Introducing liteLLM Proxy Server: Simplify AI API Endpoints with 50+ LLM Models, Error Handling, and

LLM Proxy Tutorial: 0:07:53

LLM Proxy Tutorial: Create Efficient LLM Applications with LiteLLM

Run Your Own 0:08:27

Run Your Own Local ChatGPT: Ollama WebUI

Using LiteLLM with 0:08:05

Using LiteLLM with Amazon Bedrock and AWS SageMaker

PaperQA with LiteLLM 0:08:17

PaperQA with LiteLLM and Ollama - SuperHuman RAG

🚫 Don't limit 0:04:02

🚫 Don't limit your app to ONE AI Provider

Go Production: ⚡️ 0:11:53

Go Production: ⚡️ Super FAST LLM (API) Serving with vLLM !!!

AutoGen Studio 2.0 0:15:11

AutoGen Studio 2.0 Tutorial - Skills, Multi-Agent Teams, and REAL WORLD Use Cases (NO CODE)

Using Ollama To 0:11:17

Using Ollama To Build a FULLY LOCAL 'ChatGPT Clone'

Building a local 0:05:39

Building a local ChatGPT with Chainlit, Mixtral, and Ollama

The RIGHT WAY 0:19:47

The RIGHT WAY To Build AI Agents with CrewAI (BONUS: 100% Local)

Комментарии
Автор

I found myself from not knowing that your channel existed, now finding that I frequently reference your content. This one is a key example, with the rise of open source llm models, I started using Ollama (yip you will find me commenting on your vid there), so a few days / months have passed and I need to consume both paid and my own models and use a single front end. And there you pop up. Tx for this. This helps makes sense of a very very very fast changing landscape.

DeonBands
Автор

For hosting a model on a local machine and exposing APIs for accessing that model what approach would you suggest ? Using LiteLLM and or LangChain ? Do you have a tutorial on that ?

arunavabhattacharya
Автор

Can I use liteLLM together with an OpenaiClient to "mimick" an openai model, but in fact it's using google gemini?

MrMoonsilver