Llama Index (Python)
LlamaIndex is a data framework designed for Large Language Models (LLMs) to ingest, structure, and access private or domain-specific data. It provides tools for beginners and advanced users to ingest data from various sources such as APIs, databases, PDFs, and more, and then index it into representations optimized for LLMs. This allows natural language querying and conversation with the data via query engines, chat interfaces, and LLM-powered data agents. LlamaIndex is available in Python and offers both high-level and lower-level APIs for ease of use and customization.
The Portkey - LlamaIndex integration brings advanced AI gateway capabilities, observability and prompt management to LlamaIndex's RAG framework, making it easier to build production-ready apps.
Quick Start Integration
⭐️ Using the Portkey custom models
Portkey is available as a Custom LLM in LlamaIndex making the integration simpler while allowing you to connect to multiple LLM providers (Anthropic, Azure, Huggingface, Anyscale, etc) through our powerful AI gateway.
Here's an example:
Using LlamaIndex's OpenAI model
To integrate Portkey with your existing models, you need to
Update OpenAI's baseURL to the Portkey Gateway
And add Portkey's headers
The same example above but using the OpenAI model would look like this:
Last updated