Upload 4 files

__init__.py

@@ -0,0 +1 @@
+# This file is intentionally left empty. It indicates that this directory is a package.

app.py

@@ -0,0 +1,42 @@
+
+from flask import Flask, request,jsonify
+import os
+import google.generativeai as genai
+import utils as ut
+# Load environment variables from .env file
+
+app = Flask(__name__)
+
+GEMINI_API_KEY = os.getenv('GEMINI_API_KEY')
+genai.configure(api_key=GEMINI_API_KEY)
+model = genai.GenerativeModel('gemini-1.5-flash')
+
+@app.route('/query', methods=['POST'])
+def query():
+    """
+    Handles the POST request to '/query'. Extracts the query from the request,
+    processes it through the search, concatenate, and generate functions,
+    and returns the generated answer.
+    """
+    if request.is_json:
+        # If the content type is application/json
+        query = request.json.get('query')
+    # get the data/query from streamlit app
+    print("Received query: ", query)
+    
+    # Step 1: Search and scrape articles based on the query
+    print("Step 1: searching articles")
+    articles=ut.search_articles(query)
+    print(articles)
+    # Step 2: Concatenate content from the scraped articles
+    print("Step 2: concatenating content")
+    extracted_content = ut.fetch_article_content(articles)
+    print(extracted_content)
+    # Step 3: Generate an answer using the LLM
+    print("Step 3: generating answer")
+    llm_response = ut.generate_answer(extracted_content,query)
+    # return the jsonified text back to streamlit
+    return jsonify({"response": llm_response})
+
+if __name__ == '__main__':
+    app.run(host='localhost', port=5001)

requirements.txt

@@ -0,0 +1,7 @@
+python-dotenv
+flask
+# openai==1.35.15
+requests
+streamlit
+beautifulsoup4
+google-generativeai

utils.py

@@ -0,0 +1,84 @@
+import os
+import requests
+import json
+import google.generativeai as genai
+
+# Load API keys from environment variables
+SERPER_API_KEY = os.getenv('X-API-KEY')
+GEMINI_API_KEY = os.getenv('GEMINI_API_KEY')
+genai.configure(api_key=GEMINI_API_KEY)
+model = genai.GenerativeModel('gemini-1.5-flash')
+
+def search_articles(query:str):
+    """
+    Searches for articles related to the query using Serper API.
+    Returns a list of dictionaries containing article URLs, headings, and text.
+    """
+    articles = None
+    # implement the search logic - retrieves articles
+    url = "https://google.serper.dev/search"
+
+    payload = json.dumps({
+    "q":query
+    })
+    headers = {
+    'X-API-KEY': SERPER_API_KEY,
+    'Content-Type': 'application/json'
+    }
+
+    response = requests.request("POST", url, headers=headers, data=payload)
+    articles = response.text
+    return articles
+
+
+def fetch_article_content(articles):
+    """
+    Fetches the article content, extracting headings and text.
+    """
+    content = ""
+    # implementation of fetching headings and content from the articles
+    data = json.loads(articles)
+
+    # Extract from answerBox if it exists
+    if 'answerBox' in data:
+        if 'title' in data['answerBox']:
+            content += data['answerBox']['title']+"\n"
+        if 'snippet' in data['answerBox']:
+            content += data['answerBox']['snippet']+"\n"
+
+    # Extract from organic search results
+    if 'organic' in data:
+        for result in data['organic']:
+            if 'title' in result:
+                content += result['title']+"\n"
+            if 'snippet' in result:
+                content += result['snippet']+"\n"
+
+    # Extract from peopleAlsoAsk
+    if 'peopleAlsoAsk' in data:
+        for question in data['peopleAlsoAsk']:
+            if 'title' in question:
+                content += question['title']+"\n"
+            if 'snippet' in question:
+                content += question['snippet']+"\n"
+    return content.strip()
+
+
+def generate_answer(content,query):
+    """
+    Generates an answer from the concatenated content using GPT-4.
+    The content and the user's query are used to generate a contextual answer.
+    """
+    # Create the prompt based on the content and the query
+    response = None
+    system_prompt = f"""You are a helpful assistant. Use the following context to answer the user's query. If the context doesn't contain relevant information, say so.\n
+    Below is the context : \n
+    {content}\n
+    Below is the user query:
+    {query}\n
+    Based on the user query above and the context given provide with highly accurate response for the user query . You should be very precise about the answer based on the user query and content.
+    """
+
+    response = model.generate_content(system_prompt)
+    return response.text
+