update

app.py

@@ -1,43 +1,175 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-
-# STEP 1 FROM SEMANTIC SEARCH
 from sentence_transformers import SentenceTransformer
-import torch
+import torch 
 
-# YOUR ORIGINAL MODEL SETUP AND FUNCTIONS (assumed preserved)
-model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+# Theme
+theme = gr.themes.Soft(
+    primary_hue="rose",
+    secondary_hue="zinc",
+    neutral_hue="pink"
+)
 
-careers_dict = {
-    "Highest Paying STEM Jobs": ["AI/ML Engineer", "Data Scientist", "Cloud Architect"],
-    "Most Flexible STEM Jobs": ["Web Developer", "Data Analyst", "UX Designer"],
-    "Most Creative STEM Jobs": ["UX Designer", "Game Developer", "AR/VR Developer"],
-    "Fastest Growing STEM Jobs": ["AI/ML Engineer", "Cybersecurity Analyst", "Data Scientist"],
-    "Low-Stress STEM Jobs": ["Technical Writer", "Data Analyst", "Statistician"]
+custom_css = """
+:root {
+    --background-fill-primary: #FFB6C2 !important;
+}
+.dark {
+    --background-fill-primary: #FFB6C1 !important;
 }
+"""
+
+# Load research file
+with open("research.txt", "r", encoding="utf-8") as file:
+    research_text = file.read()
+
+# Preprocess text
+def preprocess_text(text):
+    cleaned_text = text.strip()
+    chunks = cleaned_text.split("\n")
+    cleaned_chunks = [chunk.strip() for chunk in chunks if chunk.strip() != ""]
+    return cleaned_chunks
+
+cleaned_chunks = preprocess_text(research_text)
+
+# Create embeddings
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def create_embeddings(text_chunks):
+    chunk_embeddings = model.encode(text_chunks, convert_to_tensor=True)
+    return chunk_embeddings
+
+chunk_embeddings = create_embeddings(cleaned_chunks)
+
+# Get top chunks
+def get_top_chunks(query, chunk_embeddings, text_chunks):
+    query_embedding = model.encode(query, convert_to_tensor=True)
+    query_embedding_normalized = query_embedding / query_embedding.norm()
+    chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
+    similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized)
+    top_indices = torch.topk(similarities, k=3).indices
+    top_chunks = [text_chunks[i] for i in top_indices]
+    return top_chunks
+
+# Inference client
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
-# RESPONSE FUNCTION
+def respond(message, history):
+    top_results = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
+    str_top_results = '\n'.join(top_results)
+    messages = [
+        {'role': 'system', 'content': f'You are a chatbot. Complete all your sentences, do not be blunt, and do not cut yourself off. The word limit is 100 words. Start off by giving a career in a complete, kind sentence, and then if prompted by the user provide more information like salary, college course,etc. Base your response on the provided context:\n{str_top_results}'}
+    ]
+    if history:
+        messages.extend(history)
+    messages.append({'role': 'user', 'content': message})
 
-def show_info(category):
-    return "\n".join(careers_dict.get(category, ["No data available"]))
+    response = client.chat_completion(
+        messages,
+        max_tokens=1000,
+        temperature=0.2
+    )
+    return response['choices'][0]['message']['content'].strip()
 
-def resource_links(career):
-    links = {
-        "AI/Machine Learning Engineer": "Top Skills:\n1. Deep Learning - https://www.deeplearning.ai/\n2. Python Programming - https://www.learnpython.org/\n3. ML Algorithms - https://www.youtube.com/watch?v=GwIo3gDZCVQ",
-        "Data Scientist": "Top Skills:\n1. Data Visualization - https://www.kaggle.com/learn/data-visualization\n2. Python for Data Science - https://www.youtube.com/watch?v=LHBE6Q9XlzI\n3. Statistics - https://www.khanacademy.org/math/statistics-probability",
-        "Cloud Solutions Architect": "Top Skills:\n1. AWS Fundamentals - https://www.aws.training/\n2. Cloud Networking - https://www.youtube.com/watch?v=VfGW0Qiy2I0\n3. DevOps Basics - https://www.edx.org/learn/devops",
-        "Cybersecurity Analyst": "Top Skills:\n1. Threat Analysis - https://attack.mitre.org/\n2. Network Security - https://www.youtube.com/watch?v=3t4pKl5nXlI\n3. Linux Basics - https://ubuntu.com/tutorials/command-line-for-beginners",
-        "Statisticians": "Top Skills:\n1. Probability Theory - https://www.khanacademy.org/math/statistics-probability\n2. R Programming - https://www.datacamp.com/courses/free-introduction-to-r\n3. Regression Analysis - https://www.youtube.com/watch?v=ZkjP5RJLQF4",
-        "Biomedical Engineer": "Top Skills:\n1. Medical Imaging - https://www.coursera.org/learn/introduction-medical-imaging\n2. Biomechanics - https://www.youtube.com/watch?v=EZbJwaLmQxU\n3. MATLAB - https://www.mathworks.com/learn/tutorials/matlab-onramp.html"
+def display_image():
+    return "KWKbanner.png"
+
+# Explore Page Info
+def show_info(topic):
+    responses = {
+        "Highest Paying STEM Jobs": "1. AI/Machine Learning Engineer – $171,774\n2. Cloud Solutions Architect – $150,241\n3. Quantitative Analyst (Quant) – $139,949\n4. Data Scientist – $128,115\n5. Actuary – $128,147",
+        "Most Flexible STEM Jobs": "1. Software Developer\n2. Cloud Solutions Architect\n3. Data Scientist\n4. Cybersecurity Analyst\n5. Statistician",
+        "Most Creative STEM Jobs": "1. Software Developer\n2. AI/Machine Learning Engineer\n3. Biomedical Engineer\n4. Mechanical Engineer\n5. Biochemist", 
+        "Fastest Growing STEM Jobs": "1. AI/Machine Learning Engineer\n2. Cybersecurity Analyst\n3. Data Scientist\n4. Software Developer\n5. Cloud Solutions Architect", 
+        "Low-Stress STEM Jobs": "1. Statistician\n2. Mathematician\n3. Operations Research Analyst\n4. Environmental Scientist\n5. Biochemist"
+    }
+    return responses.get(topic, "Select a category to see the corresponding careers.")
+
+# Resources Page Info (HTML + Embedded Video)
+def resource_block(career):
+    resources = {
+        "AI/Machine Learning Engineer": {
+            "links": [
+                ("DeepLearning.AI", "https://www.deeplearning.ai"),
+                ("Fast.ai", "https://www.fast.ai"),
+                ("Stanford CS229", "https://cs229.stanford.edu/")
+            ],
+            "video": "https://www.youtube.com/embed/5NgNicANyqM"
+        },
+        "Data Scientist": {
+            "links": [
+                ("Kaggle Learn", "https://www.kaggle.com/learn"),
+                ("Harvard Data Science", "https://online-learning.harvard.edu/series/data-science"),
+                ("DataCamp", "https://www.datacamp.com")
+            ],
+            "video": "https://www.youtube.com/embed/xC-c7E5PK0Y"
+        },
+        "Cloud Solutions Architect": {
+            "links": [
+                ("AWS Training", "https://aws.amazon.com/training/"),
+                ("Azure Certifications", "https://learn.microsoft.com/en-us/certifications/"),
+                ("Google Cloud Boost", "https://cloudskillsboost.google/")
+            ],
+            "video": "https://www.youtube.com/embed/Y1OVgGIGvfc"
+        },
+        "Cybersecurity Analyst": {
+            "links": [
+                ("Cybrary", "https://www.cybrary.it"),
+                ("MITRE ATT&CK", "https://attack.mitre.org/"),
+                ("TryHackMe", "https://tryhackme.com")
+            ],
+            "video": "https://www.youtube.com/embed/9fWjKkFvQxg"
+        },
+        "Statisticians": {
+            "links": [
+                ("Statistics with R (Coursera)", "https://www.coursera.org/specializations/statistics"),
+                ("Khan Academy Statistics", "https://www.khanacademy.org/math/statistics-probability")
+            ],
+            "video": "https://www.youtube.com/embed/xxpc-HPKN28"
+        },
+        "Biomedical Engineer": {
+            "links": [
+                ("Johns Hopkins BME", "https://www.bme.jhu.edu/"),
+                ("edX Biomedical Courses", "https://www.edx.org/learn/biomedical-engineering"),
+                ("NIH Biomedical Research", "https://www.nih.gov/")
+            ],
+            "video": "https://www.youtube.com/embed/NM5EekDaF3g"
+        }
     }
-    return links.get(career, "Select a career to see resources.")
 
-with gr.Blocks() as demo:
+    content = resources.get(career)
+    if not content:
+        return "Select a career to see resources.", ""
+
+    link_html = "<ul>"
+    for name, url in content["links"]:
+        link_html += f'<li><a href="{url}" target="_blank">{name}</a></li>'
+    link_html += "</ul>"
+
+    video_iframe = f"""
+    <iframe width="560" height="315" src="{content['video']}" 
+    title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; 
+    clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>
+    """
+
+    return link_html, video_iframe
+
+# UI Layout
+with gr.Blocks(theme=theme, css=custom_css) as chatbot:
+    gr.Image(display_image)
+
     with gr.Tabs():
-        with gr.Tab("Chatbot"):
-            gr.Markdown("Chatbot Tab Placeholder")  # Preserve original chatbot code here
+        with gr.Tab("ChatBot"):
+            gr.ChatInterface(
+                respond,
+                type="messages",
+                title="Hi, I'm Path Pilot!",
+                textbox=gr.Textbox(placeholder="Share your interests and explore more on your career of choice!"),
+                description="This tool provides information on STEM Careers."
+            )
 
-        with gr.Tab("Explore now"):
+        with gr.Tab("Explore Page"): 
+            gr.Markdown("### Explore STEM Career Categories")
             dropdown_explore = gr.Dropdown(
                 choices=[
                     "Highest Paying STEM Jobs",
@@ -51,7 +183,8 @@ with gr.Blocks() as demo:
             output_explore = gr.Textbox(label="Top-Ranked Jobs", interactive=False)
             dropdown_explore.change(fn=show_info, inputs=dropdown_explore, outputs=output_explore)
 
-        with gr.Tab("Resources Page"):
+        with gr.Tab("Resources Page"): 
+            gr.Markdown("### Career-Specific Educational Resources")
             dropdown_resources = gr.Dropdown(
                 choices=[
                     "AI/Machine Learning Engineer",
@@ -63,9 +196,14 @@ with gr.Blocks() as demo:
                 ],
                 label="Choose a Career"
             )
-            output_resources = gr.Textbox(label="Recommended Resources", interactive=False)
-            dropdown_resources.change(fn=resource_links, inputs=dropdown_resources, outputs=output_resources)
+            output_links = gr.HTML()
+            output_video = gr.HTML()
+            dropdown_resources.change(
+                fn=resource_block,
+                inputs=dropdown_resources,
+                outputs=[output_links, output_video]
+            )
 
-demo.launch()
+chatbot.launch()