---
title: OpenHermes Mistral API
emoji: 🧠
colorFrom: gray
colorTo: blue
pinned: false
short_description: This API is for AnalyDocs
---

# 🧠 Mistral-7B GGUF API – Hosted LLM Inference with FastAPI

This Hugging Face Space hosts a lightweight, quantized version of the [Mistral-7B Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) large language model in **GGUF format (Q4_K_M)** using `llama-cpp-python` and `FastAPI`.

It exposes a simple `/generate` endpoint to allow easy integration of high-quality local inference into any application – no OpenAI keys, no vendor lock-in, no GPU dependency.

---

## 🔗 Live Demo

> 🚀 API is deployed and accessible here:  
> **https://Priyanshukr-1-openhermes_mistral_API.hf.space**

---

## 📄 Used In: AnalyDocs – AI-Powered Report Generator

**AnalyDocs** is a smart document and data report generation tool that uses this API as its core language generation engine.

### 🧠 What AnalyDocs Does:
AnalyDocs takes structured or unstructured business data (tables, charts, KPIs, raw CSVs) and transforms it into meaningful written insights using prompt-based LLM processing.

**Features:**
- ✨ Natural language summaries of documents, reports, and spreadsheets
- 📊 Automatic generation of key insights from graphs and charts
- 📈 Time-series growth/decline analysis with possible reasons from news sources
- 📝 Clean, editable paragraphs and bullet points for documentation

The LLM API hosted in this repo powers the natural language generation core of AnalyDocs.

> 🛠 Example use case:  
> “Generate a 5-point executive summary comparing Q1 and Q2 performance, highlighting changes and probable causes.”

---

## 📡 API Documentation

### **POST** `/generate`

#### Request:
```json
{
  "prompt": "Write a summary of the key growth areas in Q2 2024 for the dairy industry."
}