Beto de Paola 9ecdb5a80d Adding bitly links to update later 1 month ago
..
aws e537356d80 Fix: Updated broken documentations links and references (#856) 4 months ago
azure d62f6d3281 fix few typos 4 months ago
crusoe ef99b32e48 update refs 4 months ago
e2b-ai-analyst 330321cd02 Update README.md to remove missing preview image 4 months ago
groq 060b80fb34 remove key 3 months ago
lamini d62f6d3281 fix few typos 4 months ago
langchain e537356d80 Fix: Updated broken documentations links and references (#856) 4 months ago
llamaindex aa60f75d44 Fixed all "Open in Colab" absolute paths 4 months ago
modal 2d483aeb9d fix some spells 4 months ago
tgi ef99b32e48 update refs 4 months ago
togetherai d62f6d3281 fix few typos 4 months ago
vllm e5b999d29a Resolved merge conflicts 4 months ago
README.md 9ecdb5a80d Adding bitly links to update later 1 month ago
llama_on_prem.md 6c872b9a0f Update `hello_llama_cloud.ipynb` source 2 months ago
using_externally_hosted_llms.ipynb 0adabb243a rename more llama_recipes occurences 4 months ago

README.md

Llama 3P Integrations

<a href="https://bit.ly/llama-api-3p"><img src="https://img.shields.io/badge/Llama_API-Join_Waitlist-brightgreen?logo=meta" /></a>
<a href="https://llama.developer.meta.com/docs?utm_source=llama-cookbook&utm_medium=readme&utm_campaign=3p_integrations"><img src="https://img.shields.io/badge/Llama_API-Documentation-4BA9FE?logo=meta" /></a>

<a href="https://github.com/meta-llama/llama-models/blob/main/models/?utm_source=llama-cookbook&utm_medium=readme&utm_campaign=3p_integrations"><img alt="Llama Model cards" src="https://img.shields.io/badge/Llama_OSS-Model_cards-green?logo=meta" /></a>
<a href="https://www.llama.com/docs/overview/?utm_source=llama-cookbook&utm_medium=readme&utm_campaign=3p_integrations"><img alt="Llama Documentation" src="https://img.shields.io/badge/Llama_OSS-Documentation-4BA9FE?logo=meta" /></a>
<a href="https://huggingface.co/meta-llama"><img alt="Hugging Face meta-llama" src="https://img.shields.io/badge/Hugging_Face-meta--llama-yellow?logo=huggingface" /></a>

<a href="https://github.com/meta-llama/synthetic-data-kit"><img alt="Llama Tools Syntethic Data Kit" src="https://img.shields.io/badge/Llama_Tools-synthetic--data--kit-orange?logo=meta" /></a>
<a href="https://github.com/meta-llama/llama-prompt-ops"><img alt="Llama Tools Syntethic Data Kit" src="https://img.shields.io/badge/Llama_Tools-llama--prompt--ops-orange?logo=meta" /></a>

This folder contains example scripts and tutorials showcasing the integration of Meta Llama models with popular platforms, frameworks, and tools in the LLM ecosystem. These integrations demonstrate how to leverage Llama's capabilities across different environments and use cases.

Each folder is maintained by the respective platform-owner and contains specific examples, tutorials, and documentation for using Llama with that platform.

[!NOTE] If you'd like to add your platform here, please open a new issue with details of your examples.

Available Integrations

AWS

Examples for using Llama 3 on Amazon Bedrock, including getting started guides, prompt engineering, and React integration.

Azure

Recipes for running Llama model inference on Azure's serverless API offerings (MaaS).

Crusoe

Recipes for deploying Llama workflows on Crusoe's high-performance, sustainable cloud, including serving Llama3.1 in FP8 with vLLM.

E2B AI Analyst

AI-powered code and data analysis tool using Meta Llama and the E2B SDK, supporting data analysis, CSV uploads, and interactive charts.

Groq

Examples and templates for using Llama models with Groq's high-performance inference API.

Lamini

Integration examples with Lamini's platform, including text2sql with memory tuning.

LangChain

Cookbooks for building agents with Llama 3 and LangChain, including tool-calling agents and RAG agents using LangGraph.

LlamaIndex

Examples of using Llama with LlamaIndex for advanced RAG applications and agentic RAG.

Modal

Integration with Modal's cloud platform for running Llama models, including human evaluation examples.

TGI

Guide for serving fine-tuned Llama models with HuggingFace's text-generation-inference server, including weight merging for LoRA models.

TogetherAI

Comprehensive demos for building LLM applications using Llama on Together AI, including multimodal RAG, contextual RAG, PDF-to-podcast conversion, knowledge graphs, and structured text extraction.

vLLM

Examples for high-throughput and memory-efficient inference using vLLM with Llama models.

Additional Resources

Using Externally Hosted LLMs

Guide for working with Llama models hosted on external platforms.

Llama On-Prem

Information about on-premises deployment of Llama models.