Delete GenAI_1.ipynb

GenAI_1.ipynb

@@ -1,315 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "9633aea7-5c45-44f9-a78b-b5bc39984754",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
-    "\n",
-    "import os\n",
-    "\n",
-    "import google.generativeai as genai\n",
-    "from langchain.document_loaders import PyPDFLoader\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_google_genai import ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings\n",
-    "from langchain.vectorstores import FAISS\n",
-    "import gradio as gr\n",
-    "\n",
-    "\n",
-    "os.environ[\"MY_SECRET_KEY\"] = \"AIzaSyDRj3wAgqOCjc_D45W_u-G3y9dk5YDgxEo\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "41abde7b-366d-427e-8938-35ce7a4ed778",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#pip install pypdf\n",
-    "#!pip install faiss-cpu"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "b7e3810f-c5fb-44d7-b4b7-a30ac507d78b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "google_api_key = os.environ[\"MY_SECRET_KEY\"]\n",
-    "\n",
-    "# Check if the API key was found\n",
-    "if google_api_key:\n",
-    "    # Set the environment variable if the API key was found\n",
-    "    os.environ[\"GOOGLE_API_KEY\"] = google_api_key\n",
-    "\n",
-    "    llm = ChatGoogleGenerativeAI(\n",
-    "        model=\"gemini-pro\",  # Specify the model name\n",
-    "        google_api_key=os.environ[\"GOOGLE_API_KEY\"]\n",
-    "    )\n",
-    "else:\n",
-    "    print(\"Error: GOOGLE_API_KEY not found in Colab secrets. Please store your API key.\")\n",
-    "\n",
-    "\n",
-    "\n",
-    "genai.configure(api_key=google_api_key)\n",
-    "model = genai.GenerativeModel(\"gemini-pro\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "ef330936-8c45-4aff-b2cf-fe9dfaaf2764",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "work_dir=os.getcwd()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "a55af811-7758-4090-a5f8-748b6192971b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Current Working Directory: /Users/saurabhverma/GENAI\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Verify file existence\n",
-    "assert \"Team1.pdf\" in os.listdir(work_dir), \"Team1.pdf not found in the specified directory!\"\n",
-    "print(f\"Current Working Directory: {os.getcwd()}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "7a0a4457-2f9c-40db-9dd4-d57e3edf1fd0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load PDF and split text\n",
-    "pdf_path = \"Team1.pdf\"  # Ensure this file is uploaded to Colab\n",
-    "loader = PyPDFLoader(pdf_path)\n",
-    "documents = loader.load()\n",
-    "\n",
-    "# Split text into chunks\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=10)\n",
-    "text_chunks = text_splitter.split_documents(documents)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "b5387499-a756-49de-86b0-96a5ce712ba7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Generate embeddings\n",
-    "embeddings = GoogleGenerativeAIEmbeddings(model=\"models/embedding-001\")\n",
-    "\n",
-    "# Store embeddings in FAISS index\n",
-    "vectorstore = FAISS.from_documents(text_chunks, embeddings)\n",
-    "retriever = vectorstore.as_retriever(search_kwargs={\"k\": 4})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "35554163-75cd-4f0b-a538-565a48700245",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Set up Gemini model\n",
-    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.0-flash-001\", temperature=0)\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "e95b424b-11c1-46f3-9b4e-9e2d42d1f05d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import gradio as gr\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
-    "\n",
-    "def rag_query(query):\n",
-    "    # Retrieve relevant documents\n",
-    "    docs = retriever.get_relevant_documents(query)\n",
-    "    \n",
-    "    # Otherwise, use RAG\n",
-    "    context = \"\\n\".join([doc.page_content for doc in docs])\n",
-    "    prompt = f\"Context:\\n{context}\\n\\nQuestion: {query}\\nAnswer directly and concisely:\"\n",
-    "\n",
-    "    try:\n",
-    "        response = llm.invoke(prompt)\n",
-    "    except Exception as e:\n",
-    "        response = f\"Error in RAG processing: {str(e)}\"\n",
-    "\n",
-    "    return response.content\n",
-    "\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "552ff2fa-3c70-4054-803e-633efc7601f4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import gradio as gr\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
-    "\n",
-    "# Initialize LLM once (avoid repeated initialization)\n",
-    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.0-flash\", temperature=0)\n",
-    "\n",
-    "# Define the general query function\n",
-    "def general_query(query):\n",
-    "    try:\n",
-    "        # Define the prompt correctly\n",
-    "        prompt = PromptTemplate.from_template(\"Answer the following query: {query}\")\n",
-    "        \n",
-    "        # Create an LLM Chain\n",
-    "        chain = LLMChain(llm=llm, prompt=prompt)\n",
-    "        \n",
-    "        # Run chatbot and return response\n",
-    "        response = chain.run(query=query)\n",
-    "        \n",
-    "        return response  # Return response directly (not response.content)\n",
-    "    \n",
-    "    except Exception as e:\n",
-    "        return f\"Error: {str(e)}\"\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "ab63a509-e927-405a-985b-d07039e05e9f",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "* Running on local URL:  http://127.0.0.1:7860\n",
-      "* Running on public URL: https://efeff91c52754b11ed.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": [
-       "<div><iframe src=\"https://efeff91c52754b11ed.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": []
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "import gradio as gr\n",
-    "\n",
-    "\n",
-    "# Function to call the selected query method\n",
-    "def query_router(query, method):\n",
-    "    if method == \"Team Query\":  # Ensure exact match with dropdown options\n",
-    "        return rag_query(query)\n",
-    "    elif method == \"General Query\":\n",
-    "        return general_query(query)\n",
-    "    return \"Invalid selection!\"\n",
-    "\n",
-    "# Define local image paths\n",
-    "logo_path = \"equinix-sign.jpg\"  # Ensure this file exists\n",
-    "\n",
-    "# Custom CSS for background styling\n",
-    "custom_css = \"\"\"\n",
-    ".gradio-container {\n",
-    "    background-color: #f0f0f0;\n",
-    "    text-align: center;\n",
-    "}\n",
-    "#logo img {\n",
-    "    display: block;\n",
-    "    margin: 0 auto;\n",
-    "    max-width: 200px; /* Adjust size */\n",
-    "}\n",
-    "\"\"\"\n",
-    "\n",
-    "# Create Gradio UI\n",
-    "with gr.Blocks(css=custom_css) as ui:\n",
-    "    gr.Image(logo_path, elem_id=\"logo\", show_label=False, height=100, width=200)  # Display Logo\n",
-    "    \n",
-    "    # Title & Description\n",
-    "    gr.Markdown(\"<h1 style='text-align: center; color: black;'>Equinix Chatbot for Automation Team</h1>\")\n",
-    "    gr.Markdown(\"<p style='text-align: center; color: black;'>Ask me anything!</p>\")\n",
-    "\n",
-    "    # Input & Dropdown Section\n",
-    "    with gr.Row():\n",
-    "        query_input = gr.Textbox(label=\"Enter your query\")\n",
-    "        query_method = gr.Dropdown([\"Team Query\", \"General Query\"], label=\"Select Query Type\")\n",
-    "    \n",
-    "    # Button for submitting query\n",
-    "    submit_button = gr.Button(\"Submit\")\n",
-    "\n",
-    "    # Output Textbox\n",
-    "    output_box = gr.Textbox(label=\"Response\", interactive=False)\n",
-    "\n",
-    "    # Button Click Event\n",
-    "    submit_button.click(query_router, inputs=[query_input, query_method], outputs=output_box)\n",
-    "\n",
-    "# Launch UI\n",
-    "ui.launch(share=True)\n"
-   ]
-  }
- ],
- "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": "3.12.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}