progress

.env

@@ -1 +1,2 @@
 PERPLEXITY_AI_API = "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"
+OPENAI_API_KEY = "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"

.gitignore

@@ -0,0 +1,2 @@
+client.json
+credentials.json

drive_test.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __future__ import print_function\n",
+    "import os\n",
+    "import google.auth\n",
+    "import google_auth_oauthlib.flow\n",
+    "import googleapiclient.discovery\n",
+    "import googleapiclient.errors\n",
+    "from google.oauth2.credentials import Credentials"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Please visit this URL to authorize this application: https://accounts.google.com/o/oauth2/auth?response_type=code&client_id=165594406980-5f6scupsune6ise7dqp04ti3mmt2eqe9.apps.googleusercontent.com&redirect_uri=http%3A%2F%2Flocalhost%3A52470%2F&scope=https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive.readonly&state=TRbdRt2JQkFtZttqScUDD9N4DW7scP&access_type=offline\n"
+     ]
+    }
+   ],
+   "source": [
+    "# If modifying these SCOPES, delete the file token.json.\n",
+    "SCOPES = ['https://www.googleapis.com/auth/drive.readonly']\n",
+    "\n",
+    "def main():\n",
+    "    \"\"\"Shows basic usage of the Drive v3 API.\n",
+    "    Prints the names and ids of the first 10 files the user has access to.\n",
+    "    \"\"\"\n",
+    "    creds = None\n",
+    "    # The file token.json stores the user's access and refresh tokens, and is\n",
+    "    # created automatically when the authorization flow completes for the first time.\n",
+    "    if os.path.exists('token.json'):\n",
+    "        creds = Credentials.from_authorized_user_file('token.json', SCOPES)\n",
+    "    # If there are no (valid) credentials available, let the user log in.\n",
+    "    if not creds or not creds.valid:\n",
+    "        if creds and creds.expired and creds.refresh_token:\n",
+    "            creds.refresh(google.auth.transport.requests.Request())\n",
+    "        else:\n",
+    "            flow = google_auth_oauthlib.flow.InstalledAppFlow.from_client_secrets_file(\n",
+    "                'credentials.json', SCOPES)\n",
+    "            creds = flow.run_local_server(port=0)\n",
+    "        # Save the credentials for the next run\n",
+    "        with open('token.json', 'w') as token:\n",
+    "            token.write(creds.to_json())\n",
+    "\n",
+    "    service = googleapiclient.discovery.build('drive', 'v3', credentials=creds)\n",
+    "\n",
+    "    # Call the Drive v3 API\n",
+    "    results = service.files().list(\n",
+    "        pageSize=10, fields=\"nextPageToken, files(id, name)\").execute()\n",
+    "    items = results.get('files', [])\n",
+    "\n",
+    "    if not items:\n",
+    "        print('No files found.')\n",
+    "    else:\n",
+    "        print('Files:')\n",
+    "        for item in items:\n",
+    "            print(u'{0} ({1})'.format(item['name'], item['id']))\n",
+    "\n",
+    "if __name__ == '__main__':\n",
+    "    main()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

ds_apis.py

@@ -0,0 +1,36 @@
+import sys, os
+from fastapi import FastAPI, Form, Body
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import FileResponse, JSONResponse
+from typing import List, Dict
+from pydantic import BaseModel
+from utils import product_categorizer
+
+
+app = FastAPI()
+
+# Define allowed origins for CORS
+origins = [
+    "http://localhost:5300",
+    "http://localhost:3000",
+    # Add other allowed origins here
+]
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+
+class ProductRequest(BaseModel):
+    products: List[str]
+
+@app.post("/categorize-products/")
+async def categorize_products(request: ProductRequest):
+    categorized_output = product_categorizer(request.products)
+    return JSONResponse(content={"categorized_products": categorized_output})

utils.py

@@ -0,0 +1,160 @@
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts.prompt import PromptTemplate
+from langchain_core.output_parsers import StrOutputParser, JsonOutputParser
+import os
+import requests
+from loguru import logger
+from dotenv import load_dotenv
+load_dotenv()
+
+
+os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
+PERPLEXITYAI_API_KEY = os.getenv('PERPLEXITY_AI_API')
+llm = ChatOpenAI(model="gpt-4o")
+
+
+
+def get_chat_completion(prompt, api_key=PERPLEXITYAI_API_KEY):
+    url = "https://api.perplexity.ai/chat/completions"
+
+    payload = {
+        "model": "llama-3.1-sonar-small-128k-online",
+        "messages": [
+            {
+                "role": "system",
+                "content": "Be precise and concise."
+            },
+            {
+                "role": "user",
+                "content": prompt
+            }
+        ],
+        "temperature": 0.2,
+        "top_p": 0.9,
+        "return_citations": True,
+        "search_domain_filter": ["perplexity.ai"],
+        "return_images": False,
+        "return_related_questions": False,
+        "search_recency_filter": "month",
+        "top_k": 0,
+        "stream": False,
+        "presence_penalty": 0,
+        "frequency_penalty": 1
+    }
+    
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+    
+    response = requests.post(url, json=payload, headers=headers)
+    
+    # Check if the request was successful
+    if response.status_code == 200:
+        response_data = response.json()
+        try:
+            # Extract the message content
+            message_content = response_data['choices'][0]['message']['content']
+            return message_content
+        except (KeyError, IndexError):
+            return "Unexpected response format."
+    else:
+        return f"Request failed with status code: {response.status_code}"
+
+
+def influencer_data(search_result: str, prompt:str) -> dict:
+    logger.info(f"Formatting Influencer Data")
+    initiator_prompt = PromptTemplate(
+        template="""<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+        You are a Influencer Data Extractor AI Agent tasked with extracting information from a search result\n
+        Backstory: \n
+            A business brand is looking for some influencer in a specific location or area. He used a tool called Perplexity AI to get this data. \n
+            This is an amazing too, and yet it can struggle a bit (ai isn't perfect you know). \n 
+            The information returned by this ai can be incomplete, not properly structured and all. \n 
+            This brand needs youe help. \n 
+        This is how you will help the brand: \n 
+            1. You will be given two things, the ai search result and the prompt used to query the ai. \n
+            2. Your major interest here is formatting and making the structure right. \n 
+            3. You will process the ai result, create a JSON structure of the key information needed by the user and add the corresponding values to it. \n
+            4. The user prompt is your guide on of how the JSON should be formatted. \n
+            5. If there's are missing data or something in the ai response, send it back as NA. \n 
+            6. At the end of your processing you want to return a structured response and also make sure it in the best order as expected by the user. \n
+            
+        Return a structured JSON or dictionary as output. \n 
+        Ensure that the data is properly arranged and in a good format. \n
+        Please do this carefully and excellently. 
+        
+    <|eot_id|><|start_header_id|>user<|end_header_id|>
+    AI_SEARCH_RESULT: {search_result} \n 
+    PROMPT: {prompt}
+    
+    <|eot_id|><|start_header_id|>assistant<|end_header_id|>""",
+            input_variables=["search_result", "prompt"],
+        )
+
+    initiator_router = initiator_prompt | llm | JsonOutputParser()
+    output = initiator_router.invoke({"search_result":search_result, "prompt":prompt})
+    return output
+
+
+def combined_influencer_data(prompt: str) -> dict:
+    # Step 1: Get data using the get_chat_completion function
+    logger.info("Using Perplexity Ai to get the influencer data")
+    search_result = get_chat_completion(prompt)
+    
+    # Step 2: Process the search result using the influencer_data function
+    logger.info("Formatting the data with OpenAI")
+    formatted_data = influencer_data(search_result, prompt)
+    
+    # Step 3: Return the final output
+    return formatted_data
+
+
+product_categories = [
+    "Beauty & Skincare",
+    "Fashion & Lifestyle",
+    "Health & Fitness",
+    "Travel & Adventure",
+    "Food & Beverage",
+    "Technology & Gadgets",
+    "Gaming & Esports",
+    "Parenting & Family",
+    "Finance & Business",
+    "Wellness & Mental Health",
+    "Automotive & Motorsports",
+    "Entertainment & Pop Culture",
+    "Photography & Visual Arts",
+    "Education & Learning",
+    "Environmental & Sustainability"
+]
+
+
+def product_categorizer(product_lists: list, product_categories=product_categories) -> str:
+    logger.info(f"Categorizing products")
+    initiator_prompt = PromptTemplate(
+        template="""<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+        You are a Brand AI Agent tasked with categorizing products into categories\n
+        There are some categories given by the brand, these are the categories the products are expected to be categorized into.\n
+        You will be given a list of products and asked to categorize them.\n
+        You are meant to categorize all the given product into one category. \n 
+        You take the following steps: 
+            1. Looking into all the list of products. \n
+            2. Understand where they belong to. \n 
+            3. Look into the kist of categories. \n 
+            4. Select the category that this products falls under. \n
+            
+        You should return the selected category as output. \n 
+        Please do this carefully and correctly. 
+        
+    <|eot_id|><|start_header_id|>user<|end_header_id|>
+    PRODUCT_LISTS: {product_lists} \n 
+    PRODUCT_CATEGORY: {product_categories}
+    
+    <|eot_id|><|start_header_id|>assistant<|end_header_id|>""",
+            input_variables=["product_lists", "product_categories"],
+        )
+
+    initiator_router = initiator_prompt | llm | StrOutputParser()
+    output = initiator_router.invoke({"product_lists":product_lists, "product_categories":product_categories})
+    return output
+