Update src/core.py

src/core.py

@@ -49,4 +49,266 @@ def process_input_from_constraints(constraints, global_tech, global_tech_embeddi
     best_technologies_id = select_technologies(best_combinations)
     best_technologies = get_technologies_by_id(best_technologies_id,global_tech)
     
-    return best_technologies
+    return best_technologies
+
+
+import gradio as gr
+import pandas as pd
+import numpy as np
+import random
+import json
+
+# --- Dummy Implementations for src.services.utils and src.services.processor ---
+# These functions simulate the behavior of your actual services for the Gradio interface.
+
+def load_technologies():
+    """
+    Dummy function to simulate loading technologies and their embeddings.
+    Returns a sample DataFrame and a dummy numpy array for embeddings.
+    """
+    tech_data = {
+        'id': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+        'name': [
+            'Machine Learning', 'Cloud Computing', 'Blockchain', 'Cybersecurity',
+            'Data Analytics', 'Artificial Intelligence', 'DevOps', 'Quantum Computing',
+            'Edge Computing', 'Robotics'
+        ],
+        'description': [
+            'Algorithms for learning from data.', 'On-demand computing resources.',
+            'Decentralized ledger technology.', 'Protecting systems from threats.',
+            'Analyzing large datasets.', 'Simulating human intelligence.',
+            'Software development and operations.', 'Utilizing quantum mechanics.',
+            'Processing data near the source.', 'Automated machines.'
+        ]
+    }
+    global_tech_df = pd.DataFrame(tech_data)
+    # Simulate embeddings as random vectors
+    global_tech_embeddings_array = np.random.rand(len(global_tech_df), 128)
+    return global_tech_df, global_tech_embeddings_array
+
+def set_prompt(problem_description: str) -> str:
+    """
+    Dummy function to simulate prompt generation.
+    """
+    return f"Based on the problem: '{problem_description}', what are the key technical challenges and requirements?"
+
+def retrieve_constraints(prompt: str) -> list[str]:
+    """
+    Dummy function to simulate constraint retrieval.
+    Returns a few sample constraints based on the prompt.
+    """
+    if "security" in prompt.lower() or "secure" in prompt.lower():
+        return ["high security", "data privacy", "authentication"]
+    elif "performance" in prompt.lower() or "speed" in prompt.lower():
+        return ["low latency", "high throughput", "scalability"]
+    elif "data" in prompt.lower() or "analyze" in prompt.lower():
+        return ["data integration", "real-time analytics", "data storage"]
+    return ["cost-efficiency", "ease of integration", "maintainability", "scalability"]
+
+def stem(text_list: list[str], type_of_text: str) -> list[str]:
+    """
+    Dummy function to simulate stemming.
+    Simplistically removes 'ing', 's', 'es' from words.
+    """
+    stemmed_list = []
+    for text in text_list:
+        words = text.split()
+        stemmed_words = []
+        for word in words:
+            word = word.lower()
+            if word.endswith("ing"):
+                word = word[:-3]
+            elif word.endswith("es"):
+                word = word[:-2]
+            elif word.endswith("s"):
+                word = word[:-1]
+            stemmed_words.append(word)
+        stemmed_list.append(" ".join(stemmed_words))
+    return stemmed_list
+
+def save_dataframe(df: pd.DataFrame, filename: str):
+    """
+    Dummy function to simulate saving a DataFrame.
+    """
+    print(f"Simulating saving DataFrame to {filename}")
+    # In a real scenario, you might save to Excel: df.to_excel(filename, index=False)
+
+def save_to_pickle(data):
+    """
+    Dummy function to simulate saving data to a pickle file.
+    """
+    print(f"Simulating saving data to pickle: {type(data)}")
+
+def get_contrastive_similarities(constraints_stemmed: list[str], global_tech_df: pd.DataFrame, global_tech_embeddings: np.ndarray):
+    """
+    Dummy function to simulate getting contrastive similarities.
+    Returns a dummy similarity matrix and result similarities.
+    """
+    num_constraints = len(constraints_stemmed)
+    num_tech = len(global_tech_df)
+
+    # Simulate a similarity matrix
+    # Each row corresponds to a constraint, each column to a technology
+    matrix = np.random.rand(num_constraints, num_tech)
+    matrix = np.round(matrix, 3) # Round for better display
+
+    # Simulate result_similarities (e.g., top 3 technologies for each constraint)
+    result_similarities = {}
+    for i, constraint in enumerate(constraints_stemmed):
+        # Get top 3 tech indices for this constraint
+        top_tech_indices = np.argsort(matrix[i])[::-1][:3]
+        top_tech_names = [global_tech_df.iloc[idx]['name'] for idx in top_tech_indices]
+        top_tech_scores = [matrix[i, idx] for idx in top_tech_indices]
+        result_similarities[constraint] = list(zip(top_tech_names, top_tech_scores))
+
+    return result_similarities, matrix
+
+def find_best_list_combinations(constraints_stemmed: list[str], global_tech_df: pd.DataFrame, matrix: np.ndarray) -> list[dict]:
+    """
+    Dummy function to simulate finding best list combinations.
+    Returns a few dummy combinations of technologies.
+    """
+    best_combinations = []
+    # Simulate finding combinations that best cover constraints
+    for i in range(min(3, len(constraints_stemmed))): # Create up to 3 dummy combinations
+        combination = {
+            "technologies": [],
+            "score": round(random.uniform(0.7, 0.95), 2),
+            "covered_constraints": []
+        }
+        num_tech_in_combo = random.randint(2, 4)
+        selected_tech_ids = random.sample(global_tech_df['id'].tolist(), num_tech_in_combo)
+        for tech_id in selected_tech_ids:
+            tech_name = global_tech_df[global_tech_df['id'] == tech_id]['name'].iloc[0]
+            combination["technologies"].append({"id": tech_id, "name": tech_name})
+        
+        # Assign some random constraints to be covered
+        num_covered_constraints = random.randint(1, len(constraints_stemmed))
+        combination["covered_constraints"] = random.sample(constraints_stemmed, num_covered_constraints)
+        
+        best_combinations.append(combination)
+    return best_combinations
+
+def select_technologies(best_combinations: list[dict]) -> list[int]:
+    """
+    Dummy function to simulate selecting technologies based on best combinations.
+    Returns a list of unique technology IDs.
+    """
+    selected_ids = set()
+    for combo in best_combinations:
+        for tech in combo["technologies"]:
+            selected_ids.add(tech["id"])
+    return list(selected_ids)
+
+def get_technologies_by_id(tech_ids: list[int], global_tech_df: pd.DataFrame) -> list[dict]:
+    """
+    Dummy function to simulate retrieving technology details by ID.
+    """
+    selected_technologies = []
+    for tech_id in tech_ids:
+        tech_info = global_tech_df[global_tech_df['id'] == tech_id]
+        if not tech_info.empty:
+            selected_technologies.append(tech_info.iloc[0].to_dict())
+    return selected_technologies
+
+# --- Core Logic (Modified for Gradio Interface) ---
+
+# Load global technologies and embeddings once when the app starts
+global_tech_df, global_tech_embeddings_array = load_technologies()
+
+def process_input_gradio(problem_description: str):
+    """
+    Processes the input problem description step-by-step for Gradio.
+    Returns all intermediate results.
+    """
+    # Step 1: Set Prompt
+    prompt = set_prompt(problem_description)
+
+    # Step 2: Retrieve Constraints
+    constraints = retrieve_constraints(prompt)
+
+    # Step 3: Stem Constraints
+    constraints_stemmed = stem(constraints, "constraints")
+    save_dataframe(pd.DataFrame({"stemmed_constraints": constraints_stemmed}), "constraints_stemmed.xlsx")
+
+    # Step 4: Global Tech (already loaded, just acknowledge)
+    # save_dataframe(global_tech_df, "global_tech.xlsx") # This is already done implicitly by loading
+
+    # Step 5: Get Contrastive Similarities
+    result_similarities, matrix = get_contrastive_similarities(
+        constraints_stemmed, global_tech_df, global_tech_embeddings_array
+    )
+    save_to_pickle(result_similarities)
+
+    # Step 6: Find Best List Combinations
+    best_combinations = find_best_list_combinations(constraints_stemmed, global_tech_df, matrix)
+
+    # Step 7: Select Technologies
+    best_technologies_id = select_technologies(best_combinations)
+
+    # Step 8: Get Technologies by ID
+    best_technologies = get_technologies_by_id(best_technologies_id, global_tech_df)
+
+    # Format outputs for Gradio
+    # Convert numpy array to list of lists for better Gradio display
+    matrix_display = matrix.tolist()
+    
+    # Convert result_similarities to a more readable format for Gradio
+    result_similarities_display = {
+        k: ", ".join([f"{name} ({score:.3f})" for name, score in v])
+        for k, v in result_similarities.items()
+    }
+    
+    best_combinations_display = json.dumps(best_combinations, indent=2)
+    best_technologies_display = json.dumps(best_technologies, indent=2)
+
+    return (
+        prompt,
+        ", ".join(constraints),
+        ", ".join(constraints_stemmed),
+        "Global technologies loaded and ready.", # Acknowledge tech loading
+        str(result_similarities_display), # Convert dict to string for display
+        pd.DataFrame(matrix_display, index=constraints_stemmed, columns=global_tech_df['name']), # Display matrix as DataFrame
+        best_combinations_display,
+        ", ".join(map(str, best_technologies_id)),
+        best_technologies_display
+    )
+
+# --- Gradio Interface Setup ---
+
+# Define the input and output components
+input_problem = gr.Textbox(
+    label="Enter Problem Description",
+    placeholder="e.g., Develop a secure and scalable e-commerce platform with real-time analytics."
+)
+
+output_prompt = gr.Textbox(label="1. Generated Prompt", interactive=False)
+output_constraints = gr.Textbox(label="2. Retrieved Constraints", interactive=False)
+output_stemmed_constraints = gr.Textbox(label="3. Stemmed Constraints", interactive=False)
+output_tech_loaded = gr.Textbox(label="4. Global Technologies Status", interactive=False)
+output_similarities = gr.Textbox(label="5. Result Similarities (Constraint -> Top Technologies)", interactive=False)
+output_matrix = gr.Dataframe(label="6. Similarity Matrix (Constraints vs. Technologies)", interactive=False)
+output_best_combinations = gr.JSON(label="7. Best Technology Combinations Found", interactive=False)
+output_selected_ids = gr.Textbox(label="8. Selected Technology IDs", interactive=False)
+output_final_technologies = gr.JSON(label="9. Final Best Technologies", interactive=False)
+
+
+# Create the Gradio Interface
+gr.Interface(
+    fn=process_input_gradio,
+    inputs=input_problem,
+    outputs=[
+        output_prompt,
+        output_constraints,
+        output_stemmed_constraints,
+        output_tech_loaded,
+        output_similarities,
+        output_matrix,
+        output_best_combinations,
+        output_selected_ids,
+        output_final_technologies
+    ],
+    title="Insight Finder: Step-by-Step Technology Selection",
+    description="Enter a problem description to see how relevant technologies are identified through various processing steps.",
+    allow_flagging="never"
+).launch()