From 9b329cbc0e077e95c789d826c9c2c73f6168e766 Mon Sep 17 00:00:00 2001 From: Ashpreet Bedi Date: Mon, 5 Feb 2024 19:26:15 +0000 Subject: [PATCH] README --- README.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 594dbb3b0..143c1aa78 100644 --- a/README.md +++ b/README.md @@ -21,9 +21,11 @@ ## ✨ What is phidata? -Phidata is a toolkit for building Autonomous AI applications using function calling. +Phidata is a toolkit for building AI Assistants using function calling. -Function calling enables LLMs to achieve tasks by taking actions (function calls) and intelligently choosing their path based on the response, just like how humans solve problems. +Function calling enables LLMs to achieve tasks by calling functions and intelligently choosing their next step based on the response, just like how humans solve problems. + +![assistants](https://github.com/phidatahq/phidata/assets/22579644/a8406c12-efb3-435c-abfe-0f92b8e808f3) ## 💡How it works @@ -31,8 +33,6 @@ Function calling enables LLMs to achieve tasks by taking actions (function calls - **Step 2:** Add Tools (functions), Knowledge (vectordb) and Storage (database) - **Step 3:** Serve using Streamlit, FastApi or Django to build your AI application -![assistants](https://github.com/phidatahq/phidata/assets/22579644/a8406c12-efb3-435c-abfe-0f92b8e808f3) - ## 👩‍💻 Getting Started ### Installation @@ -62,10 +62,10 @@ python assistant.py ## ⭐️ Use phidata to build -- **Data Assistants:** Analyze data by running SQL queries. -- **Python Assistants:** Perform tasks by running python code. - **Knowledge Assistants:** Answer questions from documents (PDFs, text) - **Research Assistants:** Perform research and summarize findings. +- **Data Assistants:** Analyze data by running SQL queries. +- **Python Assistants:** Perform tasks by running python code. - **Customer Assistants:** Answer customer queries using product descriptions and purchase history. - **Marketing Assistants:** Provide marketing insights, copywriting and content ideas. - **Travel Assistants:** Help plan travel by researching destinations, flight and hotel prices. @@ -74,7 +74,7 @@ python assistant.py ## 🚀 Demos - PDF AI that summarizes and answers questions from PDFs. -- arXiv AI that summarizes and answers questions about arXiv papers. +- arXiv AI that answers questions about ArXiv papers using the ArXiv API. - HackerNews AI that interacts with the HN API to summarize stories, users, find out what's trending, summarize topics. - Demo Streamlit App serving a PDF, Image and Website Assistant (password: admin) - Demo FastApi serving a PDF Assistant. @@ -83,7 +83,7 @@ python assistant.py ## 🎖️ Templates -After building an Assistant, serve it using **Streamlit**, **FastApi** or **Django** to build an AI application. +After building an Assistant, serve it using **Streamlit**, **FastApi** or **Django** to build your AI application. Instead of wiring these tools manually, phidata provides **pre-built** templates for AI Apps that you can run locally or deploy to AWS with 1 command. Here's how they work: - Create your AI App using a template: `phi ws create`