Prem

Welcome to Prem

Let's create a Generative AI application in minutes.

Quickstart Guide

Set up Prem SDK

Monitoring and Tracing

Autonomous Fine-Tuning

Structured Output

Function Calling

The [chat completion](/api-reference/chat-completions/post-v1chatcompletions) endpoint provides a way to generate chat completions based on provided input messages. This endpoint supports streaming via Server-Sent Events (SSE), allowing for partial message deltas to be sent back to the client.

Streaming Chat

Prompt Templates

This example explains how to access different LLMs and Embedding Models in Llamaindex through PremAI SDK.

LlamaIndex

This example goes over how to use LangChain to interact with different chat models using langchain `ChatPremAI`

LangChain

This example explains how to use DsPY by Stanford NLP to interact with different chat models.

DSPy

Qdrant is a vector similarity search engine. It provides a production-ready service with a convenient API to store, search, and manage points - vectors with an additional payload. Qdrant is tailored to extended filtering support. It makes it useful for all sorts of neural network or semantic-based matching, faceted search, and other applications.

Qdrant

Learn how to interact with Prem's API endpoints.

Introduction

Creates a model response for the given chat conversation. Supports streaming with SSE, [documentation here](https://docs.premai.io/get-started/chat-completion-sse).

Post v1create finetuning job

Post v1delete finetuning job

Post v1download finetuned model

Post v1finetuned model try

Post v1finetuning job details

Post v1init page data

Release Notes

Community

Blog

Models' Status

API Reference

Use Prem

Support

PREM Cookbook Repository

Chat with PDF

URL Content Summarizer

Generate SQL from Text

Chat with SQL Tables

Paper search and QnA on ArXiv papers

Learn how to use and customize premsql datasets for Text-to-SQL tasks, including working with available datasets, creating your own, and extending functionalities.

Datasets

Models that generate SQL queries from user input and a specified database source.

Generators

Connects to databases and executes generated SQL queries to fetch results.

Executors

Evaluates different Text to SQL models and pipelines with standard benchmarks and metrics.

Evaluators

Helps to make error handling prompts and datasets for error free inference and fine-tuning datasets for enforcing self correction property.

Error Handling

Helps to fine-tune Open Source models using different readily available datasets or custom datasets for Text to SQL tasks.

Tuner

End-to-end workflows customizable Text to SQL Agentic workflows for querying, analysing and plotting charts in databases all in natural language.

Agents

Agent Server where you can deploy PremSQL agents in the most customized forms.

API Documentation

repositories

repository-document

chat-completions

finetuning

embeddings

v1

models

feedbacks

traces

Post v1repositories