Upload 3 files

app.py

@@ -1,64 +1,60 @@
+# Importing necessary libraries
+import json
+import numpy as np
+from sentence_transformers import SentenceTransformer, util
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+# Load your course data
+with open("courses.json", "r") as f:
+    courses = json.load(f)
+
+# Initialize model for embedding generation
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# Generate embeddings for all course descriptions
+course_descriptions = [course["description"] for course in courses]
+course_embeddings = model.encode(course_descriptions, convert_to_tensor=True)
+
+# Function to perform smart search
+def search_courses(query):
+    # Generate embedding for the search query
+    query_embedding = model.encode(query, convert_to_tensor=True)
+
+    # Compute cosine similarities between the query and all course descriptions
+    similarities = util.pytorch_cos_sim(query_embedding, course_embeddings)[0]
+
+    # Find the top 5 most similar courses
+    top_results = np.argsort(similarities, descending=True)[:5]
+
+    # Prepare output
+    results = []
+    for idx in top_results:
+        course = courses[idx]
+        results.append({
+            "Title": course["title"],
+            "Description": course["description"],
+            "Link": course["link"]
+        })
+    return results
+
+# Gradio Interface
+def search_interface(query):
+    # Call the search function and format results
+    results = search_courses(query)
+    display_text = "\n\n".join(
+        [f"**Title**: {result['Title']}\n\n**Description**: {result['Description']}\n\n[Go to course]({result['Link']})" for result in results]
+    )
+    return display_text
+
+# Creating the Gradio UI
+iface = gr.Interface(
+    fn=search_interface,
+    inputs="text",
+    outputs="markdown",
+    title="Analytics Vidhya Free Courses - Smart Search",
+    description="Enter a topic or keywords to find the most relevant free courses on Analytics Vidhya.",
+    examples=["Machine Learning", "Data Science", "Python for Beginners"]
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio interface
+iface.launch()

courses.json

@@ -0,0 +1,12 @@
+[
+    {
+        "title": "Framework to Choose the Right LLM for your Business",
+        "description": "This course provides a comprehensive framework for selecting the right LLM for your business. Learn to evaluate LLMs based on accuracy, cost, scalability, and more, while exploring real-world applications to make informed, strategic AI decisions.",
+        "link": "https://courses.analyticsvidhya.com/courses/choosing-the-right-LLM-for-your-business"
+    },
+    {
+        "title": "Improving Real World RAG Systems: Key Challenges & Practical Solutions",
+        "description": "Description of Course 2.",
+        "link": "https://courses.analyticsvidhya.com/courses/improving-real-world-rag-systems-key-challenges"
+    }
+]

requirements (1).txt

@@ -0,0 +1,4 @@
+sentence-transformers
+gradio
+torch
+numpy