From 9f1209827932eb07e62ccbfcc0615fd564553ace Mon Sep 17 00:00:00 2001 From: johnIT56 Date: Sat, 22 Feb 2025 14:37:26 +0900 Subject: [PATCH] Ollama_gradio --- .../day3-ollama-gradio.ipynb | 377 ++++++++++++++++++ 1 file changed, 377 insertions(+) create mode 100644 week2/community-contributions/day3-ollama-gradio.ipynb diff --git a/week2/community-contributions/day3-ollama-gradio.ipynb b/week2/community-contributions/day3-ollama-gradio.ipynb new file mode 100644 index 0000000..f2001b6 --- /dev/null +++ b/week2/community-contributions/day3-ollama-gradio.ipynb @@ -0,0 +1,377 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "75e2ef28-594f-4c18-9d22-c6b8cd40ead2", + "metadata": {}, + "source": [ + "# Day 3 - Conversational AI - aka Chatbot!" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "70e39cd8-ec79-4e3e-9c26-5659d42d0861", + "metadata": {}, + "outputs": [], + "source": [ + "# imports\n", + "\n", + "import os\n", + "import ollama\n", + "import gradio as gr" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "6541d58e-2297-4de1-b1f7-77da1b98b8bb", + "metadata": {}, + "outputs": [], + "source": [ + "# Initialize\n", + "MODEL_LLAMA = 'llama3.2'" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "e16839b5-c03b-4d9d-add6-87a0f6f37575", + "metadata": {}, + "outputs": [], + "source": [ + "system_message = \"You are a helpful assistant\"" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "1eacc8a4-4b48-4358-9e06-ce0020041bc1", + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "\n", + "def chat(message, history):\n", + " messages = [{\"role\": \"system\", \"content\": system_message}] + history + [{\"role\": \"user\", \"content\": message}]\n", + "\n", + " print(\"History is:\")\n", + " print(history)\n", + " print(\"And messages is:\")\n", + " print(messages)\n", + "\n", + " stream = ollama.chat(model=MODEL_LLAMA, messages=messages, stream=True)\n", + "\n", + " response_text = \"\"\n", + " for chunk in stream:\n", + " response_text += chunk['message']['content']\n", + " yield response_text" + ] + }, + { + "cell_type": "markdown", + "id": "1334422a-808f-4147-9c4c-57d63d9780d0", + "metadata": {}, + "source": [ + "## And then enter Gradio's magic!" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "0866ca56-100a-44ab-8bd0-1568feaf6bf2", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7861\n", + "* Running on public URL: https://6539f61952f430fa2d.gradio.live\n", + "\n", + "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "History is:\n", + "[]\n", + "And messages is:\n", + "[{'role': 'system', 'content': 'You are a helpful assistant'}, {'role': 'user', 'content': 'hello'}]\n" + ] + } + ], + "source": [ + "gr.ChatInterface(fn=chat, type=\"messages\").launch(share=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "1f91b414-8bab-472d-b9c9-3fa51259bdfe", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, + "outputs": [], + "source": [ + "system_message = \"You are a helpful assistant in a clothes store. You should try to gently encourage \\\n", + "the customer to try items that are on sale. Hats are 60% off, and most other items are 50% off. \\\n", + "For example, if the customer says 'I'm looking to buy a hat', \\\n", + "you could reply something like, 'Wonderful - we have lots of hats - including several that are part of our sales event.'\\\n", + "Encourage the customer to buy hats if they are unsure what to get.\"" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "4e5be3ec-c26c-42bc-ac16-c39d369883f6", + "metadata": {}, + "outputs": [], + "source": [ + "def chat(message, history):\n", + " messages = [{\"role\": \"system\", \"content\": system_message}] + history + [{\"role\": \"user\", \"content\": message}]\n", + "\n", + "\n", + " stream = ollama.chat(model=MODEL_LLAMA, messages=messages, stream=True)\n", + "\n", + " response_text = \"\"\n", + " for chunk in stream:\n", + " response_text += chunk['message']['content']\n", + " yield response_text" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "413e9e4e-7836-43ac-a0c3-e1ab5ed6b136", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7862\n", + "* Running on public URL: https://79f09af36adcf63688.gradio.live\n", + "\n", + "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gr.ChatInterface(fn=chat, type=\"messages\").launch(share=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "d75f0ffa-55c8-4152-b451-945021676837", + "metadata": {}, + "outputs": [], + "source": [ + "system_message += \"\\nIf the customer asks for shoes, you should respond that shoes are not on sale today, \\\n", + "but remind the customer to look at hats!\"" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "c602a8dd-2df7-4eb7-b539-4e01865a6351", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7863\n", + "* Running on public URL: https://30446ba4b8f125e235.gradio.live\n", + "\n", + "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gr.ChatInterface(fn=chat, type=\"messages\").launch(share=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "5b128796-1bea-445d-9e3b-8321ca822257", + "metadata": {}, + "outputs": [], + "source": [ + "def chat(message, history):\n", + "\n", + " relevant_system_message = system_message\n", + " if 'belt' in message:\n", + " relevant_system_message += \" The store does not sell belts; if you are asked for belts, be sure to point out other items on sale.\"\n", + " \n", + " messages = [{\"role\": \"system\", \"content\": relevant_system_message}] + history + [{\"role\": \"user\", \"content\": message}]\n", + "\n", + "\n", + " stream = ollama.chat(model=MODEL_LLAMA, messages=messages, stream=True)\n", + "\n", + " response_text = \"\"\n", + " for chunk in stream:\n", + " response_text += chunk['message']['content']\n", + " yield response_text" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "20570de2-eaad-42cc-a92c-c779d71b48b6", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "* Running on local URL: http://127.0.0.1:7865\n", + "* Running on public URL: https://3933c80bf256709cf9.gradio.live\n", + "\n", + "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n" + ] + }, + { + "data": { + "text/html": [ + "
" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gr.ChatInterface(fn=chat, type=\"messages\").launch(share=True)" + ] + }, + { + "cell_type": "markdown", + "id": "82a57ee0-b945-48a7-a024-01b56a5d4b3e", + "metadata": {}, + "source": [ + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \n", + "

Business Applications

\n", + " Conversational Assistants are of course a hugely common use case for Gen AI, and the latest frontier models are remarkably good at nuanced conversation. And Gradio makes it easy to have a user interface. Another crucial skill we covered is how to use prompting to provide context, information and examples.\n", + "

\n", + "Consider how you could apply an AI Assistant to your business, and make yourself a prototype. Use the system prompt to give context on your business, and set the tone for the LLM.
\n", + "
" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6dfb9e21-df67-4c2b-b952-5e7e7961b03d", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.13.2" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}