Update app.py

app.py

@@ -17,25 +17,28 @@ import re
 from datetime import datetime, timedelta
 from pathlib import Path
 import torch
+import numpy as np
 
 # Load environment variables
 load_dotenv()
 client = groq.Client(api_key=os.getenv("GROQ_TECH_API_KEY"))
 
-# Replace the embeddings initialization
+# Initialize embeddings with error handling
 try:
-    # Initialize embeddings with a simpler, more reliable model
     embeddings = HuggingFaceInstructEmbeddings(
         model_name="hkunlp/instructor-base",
         model_kwargs={"device": "cuda" if torch.cuda.is_available() else "cpu"}
     )
 except Exception as e:
     print(f"Warning: Failed to load primary embeddings model: {e}")
-    # Fallback to a basic model
-    embeddings = HuggingFaceInstructEmbeddings(
-        model_name="all-MiniLM-L6-v2",
-        model_kwargs={"device": "cuda" if torch.cuda.is_available() else "cpu"}
-    )
+    try:
+        embeddings = HuggingFaceInstructEmbeddings(
+            model_name="all-MiniLM-L6-v2",
+            model_kwargs={"device": "cuda" if torch.cuda.is_available() else "cpu"}
+        )
+    except Exception as e:
+        print(f"Warning: Failed to load fallback embeddings model: {e}")
+        embeddings = None
 
 # Directory to store FAISS indexes
 FAISS_INDEX_DIR = "faiss_indexes_tech"
@@ -48,44 +51,75 @@ user_vectorstores = {}
 # Custom CSS for Tech theme
 custom_css = """
 :root {
-    --primary-color: #4285F4;  /* Google Blue */
-    --secondary-color: #34A853;  /* Google Green */
+    --primary-color: #4285F4;
+    --secondary-color: #34A853;
+    --accent-color: #EA4335;
     --light-background: #F8F9FA;
     --dark-text: #202124;
     --white: #FFFFFF;
     --border-color: #DADCE0;
     --code-bg: #F1F3F4;
-    --code-text: #37474F;
-    --error-color: #EA4335;  /* Google Red */
-    --warning-color: #FBBC04;  /* Google Yellow */
 }
-body { background-color: var(--light-background); font-family: 'Google Sans', 'Roboto', sans-serif; }
-.container { max-width: 1200px !important; margin: 0 auto !important; padding: 10px; }
-.header { background-color: var(--white); border-bottom: 1px solid var(--border-color); padding: 15px 0; margin-bottom: 20px; border-radius: 12px 12px 0 0; box-shadow: 0 1px 2px rgba(0,0,0,0.05); }
-.header-title { color: var(--primary-color); font-size: 1.8rem; font-weight: 700; text-align: center; }
-.header-subtitle { color: var(--dark-text); font-size: 1rem; text-align: center; margin-top: 5px; }
-.chat-container { border-radius: 8px !important; box-shadow: 0 1px 3px rgba(0,0,0,0.1) !important; background-color: var(--white) !important; border: 1px solid var(--border-color) !important; min-height: 500px; }
-.message-user { background-color: var(--primary-color) !important; color: var(--white) !important; border-radius: 18px 18px 4px 18px !important; padding: 12px 16px !important; margin-left: auto !important; max-width: 80% !important; }
-.message-bot { background-color: #F1F3F4 !important; color: var(--dark-text) !important; border-radius: 18px 18px 18px 4px !important; padding: 12px 16px !important; margin-right: auto !important; max-width: 80% !important; }
-.input-area { background-color: var(--white) !important; border-top: 1px solid var(--border-color) !important; padding: 12px !important; border-radius: 0 0 12px 12px !important; }
-.input-box { border: 1px solid var(--border-color) !important; border-radius: 24px !important; padding: 12px 16px !important; box-shadow: 0 1px 2px rgba(0,0,0,0.05) !important; }
-.send-btn { background-color: var(--primary-color) !important; border-radius: 24px !important; color: var(--white) !important; padding: 10px 20px !important; font-weight: 500 !important; }
-.clear-btn { background-color: #F1F3F4 !important; border: 1px solid var(--border-color) !important; border-radius: 24px !important; color: var(--dark-text) !important; padding: 8px 16px !important; font-weight: 500 !important; }
-.pdf-viewer-container { border-radius: 8px !important; box-shadow: 0 1px 3px rgba(0,0,0,0.1) !important; background-color: var(--white) !important; border: 1px solid var(--border-color) !important; padding: 20px; }
-.pdf-viewer-image { max-width: 100%; height: auto; border: 1px solid var(--border-color); border-radius: 8px; box-shadow: 0 1px 2px rgba(0,0,0,0.05); }
-.stats-box { background-color: #E8F0FE; padding: 10px; border-radius: 8px; margin-top: 10px; }
-.tool-container { background-color: var(--white); border-radius: 8px; box-shadow: 0 1px 3px rgba(0,0,0,0.1); padding: 15px; margin-bottom: 20px; border: 1px solid var(--border-color); }
-.code-block { background-color: var(--code-bg); color: var(--code-text); padding: 12px; border-radius: 8px; font-family: 'Roboto Mono', monospace; overflow-x: auto; margin: 10px 0; border-left: 3px solid var(--primary-color); }
-.repo-card { border: 1px solid var(--border-color); padding: 15px; margin: 10px 0; border-radius: 8px; background-color: var(--white); }
-.repo-name { color: var(--primary-color); font-weight: bold; font-size: 1.1rem; margin-bottom: 5px; }
-.repo-description { color: var(--dark-text); font-size: 0.9rem; margin-bottom: 10px; }
-.repo-stats { display: flex; gap: 15px; color: #5F6368; font-size: 0.85rem; }
-.repo-stat { display: flex; align-items: center; gap: 5px; }
-.qa-card { border-left: 3px solid var(--secondary-color); padding: 10px 15px; margin: 15px 0; background-color: #F8F9FA; border-radius: 0 8px 8px 0; }
-.qa-title { font-weight: bold; color: var(--dark-text); margin-bottom: 5px; }
-.qa-body { color: var(--dark-text); font-size: 0.95rem; margin-bottom: 10px; }
-.qa-meta { display: flex; justify-content: space-between; color: #5F6368; font-size: 0.85rem; }
-.tag { background-color: #E8F0FE; color: var(--primary-color); padding: 4px 8px; border-radius: 4px; font-size: 0.8rem; margin-right: 5px; display: inline-block; }
+
+body { 
+    background-color: var(--light-background); 
+    font-family: 'Google Sans', 'Roboto', sans-serif; 
+}
+
+.container { 
+    max-width: 1200px !important; 
+    margin: 0 auto !important; 
+    padding: 10px; 
+}
+
+.header { 
+    background-color: var(--white);
+    border-bottom: 1px solid var(--border-color);
+    padding: 15px 0;
+    margin-bottom: 20px;
+    border-radius: 12px 12px 0 0;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.05);
+}
+
+.header-title { 
+    color: var(--primary-color);
+    font-size: 1.8rem;
+    font-weight: 700;
+    text-align: center;
+}
+
+.header-subtitle { 
+    color: var(--dark-text);
+    font-size: 1rem;
+    text-align: center;
+    margin-top: 5px;
+}
+
+.chat-container { 
+    border-radius: 12px !important;
+    box-shadow: 0 4px 6px rgba(0,0,0,0.1) !important;
+    background-color: var(--white) !important;
+    border: 1px solid var(--border-color) !important;
+    min-height: 500px;
+}
+
+.tool-container { 
+    background-color: var(--white);
+    border-radius: 12px;
+    box-shadow: 0 4px 6px rgba(0,0,0,0.1);
+    padding: 15px;
+    margin-bottom: 20px;
+}
+
+.code-block { 
+    background-color: var(--code-bg);
+    padding: 12px;
+    border-radius: 8px;
+    font-family: 'Roboto Mono', monospace;
+    overflow-x: auto;
+    margin: 10px 0;
+    border-left: 3px solid var(--primary-color);
+}
 """
 
 # Function to process PDF files
@@ -127,68 +161,28 @@ def process_pdf(pdf_file):
 
 # Function to generate chatbot responses with Tech theme
 def generate_response(message, session_id, model_name, history):
+    """Generate chatbot responses"""
     if not message:
         return history
+    
     try:
         context = ""
-        if embeddings and session_id and session_id in user_vectorstores:  # Check if embeddings exist
+        if embeddings and session_id and session_id in user_vectorstores:
             try:
                 vectorstore = user_vectorstores[session_id]
                 docs = vectorstore.similarity_search(message, k=3)
                 if docs:
-                    context = "\n\nRelevant information from uploaded code:\n" + "\n".join(f"- {doc.page_content}" for doc in docs)
+                    context = "\n\nRelevant code context:\n" + "\n".join(f"```\n{doc.page_content}\n```" for doc in docs)
             except Exception as e:
                 print(f"Warning: Failed to perform similarity search: {e}")
         
-        # Check if it's a GitHub repo search
-        if re.match(r'^/github\s+.+', message, re.IGNORECASE):
-            query = re.sub(r'^/github\s+', '', message, flags=re.IGNORECASE)
-            repo_results = search_github_repos(query)
-            if repo_results:
-                response = "**GitHub Repository Search Results:**\n\n"
-                for repo in repo_results[:3]:  # Limit to top 3 results
-                    response += f"**[{repo['name']}]({repo['html_url']})**\n"
-                    if repo['description']:
-                        response += f"{repo['description']}\n"
-                    response += f"⭐ {repo['stargazers_count']} | 🍴 {repo['forks_count']} | Language: {repo['language'] or 'Not specified'}\n"
-                    response += f"Updated: {repo['updated_at'][:10]}\n\n"
-                history.append({"role": "assistant", "content": response})
-                return history
-            else:
-                history.append({"role": "assistant", "content": "No GitHub repositories found for your query."})
-                return history
-        
-        # Check if it's a Stack Overflow search
-        if re.match(r'^/stack\s+.+', message, re.IGNORECASE):
-            query = re.sub(r'^/stack\s+', '', message, flags=re.IGNORECASE)
-            qa_results = search_stackoverflow(query)
-            if qa_results:
-                response = "**Stack Overflow Search Results:**\n\n"
-                for qa in qa_results[:3]:  # Limit to top 3 results
-                    response += f"**[{qa['title']}]({qa['link']})**\n"
-                    response += f"Score: {qa['score']} | Answers: {qa['answer_count']}\n"
-                    if 'tags' in qa and qa['tags']:
-                        response += f"Tags: {', '.join(qa['tags'][:5])}\n"
-                    response += f"Asked: {qa['creation_date']}\n\n"
-                history.append({"role": "assistant", "content": response})
-                return history
-            else:
-                history.append({"role": "assistant", "content": "No Stack Overflow questions found for your query."})
-                return history
+        system_prompt = """You are a technical assistant specializing in software development and programming.
+        Provide clear, accurate responses with code examples when relevant.
+        Format code snippets with proper markdown code blocks and specify the language."""
         
-        # Check if it's a code explanation request
-        code_match = re.search(r'/explain\s+```(?:.+?)?\n(.+?)```', message, re.DOTALL)
-        if code_match:
-            code = code_match.group(1).strip()
-            explanation = explain_code(code)
-            history.append({"role": "assistant", "content": explanation})
-            return history
-                
-        system_prompt = "You are a technical assistant specializing in software development, programming, and IT topics."
-        system_prompt += " Format code snippets with proper markdown code blocks with language specified."
-        system_prompt += " For technical explanations, be precise and include examples where helpful."
         if context:
-            system_prompt += " Use the following context to answer the question if relevant: " + context
+            system_prompt += f"\nUse this context from the uploaded code when relevant:{context}"
+        
         completion = client.chat.completions.create(
             model=model_name,
             messages=[
@@ -198,11 +192,14 @@ def generate_response(message, session_id, model_name, history):
             temperature=0.7,
             max_tokens=1024
         )
+        
         response = completion.choices[0].message.content
         history.append({"role": "assistant", "content": response})
         return history
+        
     except Exception as e:
-        history.append({"role": "assistant", "content": f"Error generating response: {str(e)}"})
+        error_msg = f"Error generating response: {str(e)}"
+        history.append({"role": "assistant", "content": error_msg})
         return history
 
 # Functions to update PDF viewer
@@ -457,6 +454,7 @@ def process_code_file(file_obj):
     """Process uploaded code files"""
     if file_obj is None:
         return None, "No file uploaded", {}
+    
     try:
         content = file_obj.read().decode('utf-8')
         file_extension = Path(file_obj.name).suffix.lower()
@@ -465,7 +463,8 @@ def process_code_file(file_obj):
         # Calculate metrics
         metrics = calculate_complexity_metrics(content, language)
         
-        # Only create vectorstore if embeddings are available
+        # Create vectorstore if embeddings are available
+        session_id = None
         if embeddings:
             try:
                 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
@@ -477,9 +476,6 @@ def process_code_file(file_obj):
                 user_vectorstores[session_id] = vectorstore
             except Exception as e:
                 print(f"Warning: Failed to create vectorstore: {e}")
-                session_id = None
-        else:
-            session_id = None
         
         return session_id, f"✅ Successfully analyzed {file_obj.name}", metrics
     except Exception as e:
@@ -492,8 +488,8 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
     
     gr.HTML("""
     <div class="header">
-        <div class="header-title">Tech-Vision</div>
-        <div class="header-subtitle">Advanced Code Analysis System</div>
+        <div class="header-title">Tech-Vision AI</div>
+        <div class="header-subtitle">Advanced Code Analysis & Technical Assistant</div>
     </div>
     """)
     
@@ -501,21 +497,15 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
         with gr.Column(scale=1, min_width=300):
             file_input = gr.File(
                 label="Upload Code File",
-                file_types=[
-                    ".py", ".js", ".java", ".cpp", ".c", ".cs", ".php",
-                    ".rb", ".go", ".rs", ".swift", ".kt", ".ts", ".html",
-                    ".css", ".sql", ".r", ".m", ".h", ".hpp", ".jsx",
-                    ".tsx", ".vue", ".scala", ".pl", ".sh", ".bash",
-                    ".ps1", ".yaml", ".yml", ".json", ".xml", ".toml", ".ini"
-                ],
+                file_types=[".py", ".js", ".java", ".cpp", ".c", ".cs", ".php", ".rb", ".go", ".ts"],
                 type="binary"
             )
             upload_button = gr.Button("Analyze Code", variant="primary")
             file_status = gr.Markdown("No file uploaded yet")
             model_dropdown = gr.Dropdown(
-                choices=["llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma-7b-it"],
+                choices=["llama3-70b-8192", "mixtral-8x7b-32768", "gemma-7b-it"],
                 value="llama3-70b-8192",
-                label="Select Groq Model"
+                label="Select Model"
             )
             
             # Developer Tools Section
@@ -672,7 +662,7 @@ if __name__ == "__main__":
 
 # Add new helper functions
 def detect_language(extension):
-    """Map file extensions to programming languages"""
+    """Detect programming language from file extension"""
     extension_map = {
         ".py": "Python",
         ".js": "JavaScript",
@@ -683,24 +673,7 @@ def detect_language(extension):
         ".php": "PHP",
         ".rb": "Ruby",
         ".go": "Go",
-        ".rs": "Rust",
-        ".swift": "Swift",
-        ".kt": "Kotlin",
-        ".ts": "TypeScript",
-        ".html": "HTML",
-        ".css": "CSS",
-        ".sql": "SQL",
-        ".r": "R",
-        ".scala": "Scala",
-        ".pl": "Perl",
-        ".sh": "Shell",
-        ".yaml": "YAML",
-        ".yml": "YAML",
-        ".json": "JSON",
-        ".xml": "XML",
-        ".jsx": "React JSX",
-        ".tsx": "React TSX",
-        ".vue": "Vue",
+        ".ts": "TypeScript"
     }
     return extension_map.get(extension.lower(), "Unknown")
 
@@ -711,26 +684,13 @@ def calculate_complexity_metrics(content, language):
     blank_lines = len([line for line in lines if not line.strip()])
     code_lines = total_lines - blank_lines
     
-    # Get language patterns
-    patterns = LANGUAGE_PATTERNS.get(language.lower(), LANGUAGE_PATTERNS.get("python"))
-    
-    # Calculate metrics using patterns
     metrics = {
         "language": language,
         "total_lines": total_lines,
         "code_lines": code_lines,
-        "blank_lines": blank_lines,
-        "functions": len(re.findall(patterns["function"], content, re.MULTILINE)) if patterns else 0,
-        "classes": len(re.findall(patterns["class"], content, re.MULTILINE)) if patterns else 0,
-        "imports": len(re.findall(patterns["import"], content, re.MULTILINE)) if patterns else 0,
-        "comments": len(re.findall(patterns["comment"], content, re.MULTILINE)) if patterns else 0,
-        "conditionals": len(re.findall(patterns["conditional"], content, re.MULTILINE)) if patterns else 0,
-        "loops": len(re.findall(patterns["loop"], content, re.MULTILINE)) if patterns else 0,
+        "blank_lines": blank_lines
     }
     
-    # Calculate cyclomatic complexity
-    metrics["cyclomatic_complexity"] = 1 + metrics["conditionals"] + metrics["loops"]
-    
     return metrics
 
 def generate_recommendations(metrics):