Upload 2 files

app.py

@@ -0,0 +1,147 @@
+import streamlit as st
+from openai_client import (
+    get_code_review_response,
+    refactor_code,
+    code_feedback,
+    suggest_best_practices,
+    remove_code_errors,
+)
+
+
+def main():
+    st.title("CodeMentor - (AI-Enhanced Code Collaboration Tool)")
+    st.subheader("Collaborate, Refactor, and Optimize with AI.")
+    st.write(
+        "A smart tool for distributed teams to automate code reviews, refactor efficiently, and get real-time AI-driven feedback."
+    )
+
+    # Instructions
+    st.write(
+        "Upload a file or paste your code below to get an AI-generated code review."
+    )
+
+    # Input Methods: File Upload or Text Area
+    uploaded_file = st.file_uploader(
+        "Upload a code file (Max 500 lines)", type=["py", "js", "txt"]
+    )
+    code_input = st.text_area("Or paste your code here (Max 1000 words)", height=300)
+
+    # Limit input size for code
+    if uploaded_file:
+        code = uploaded_file.read().decode("utf-8")
+        if len(code.splitlines()) > 500:
+            st.error(
+                "File is too large! Please upload a file with a maximum of 500 lines."
+            )
+            code = None  # Reset code if it's too large
+        else:
+            st.success(f"File uploaded: {uploaded_file.name}")
+    elif code_input:
+        code = code_input
+        if len(code.split()) > 1000:
+            st.error("Code exceeds 1000 words! Please shorten your code.")
+            code = None  # Reset code if it's too large
+    else:
+        code = None
+
+    # Button to trigger code review
+    if st.button("Get Code Review") and code:
+        with st.spinner("Processing..."):
+            # Call the OpenAI API to get code review
+            review = get_code_review_response(code)
+            st.subheader("Code Review Results:")
+            st.write(review)
+
+            # Provide download option
+            st.download_button(
+                label="Download Code Review",
+                data=review,
+                file_name="code_review.txt",
+                mime="text/plain",
+            )
+            st.success("You can download the code review as code_review.txt")
+
+        # Button to trigger code refactoring
+    if st.button("Refactor Code") and code:
+        with st.spinner("Refactoring your code..."):
+            refactored_code = refactor_code(code)
+            st.subheader("Refactored Code:")
+            st.write(refactored_code)
+
+            # Provide download option for refactored code
+            st.download_button(
+                label="Download Refactored Code",
+                data=refactored_code,
+                file_name="refactored_code.txt",
+                mime="text/plain",
+            )
+            st.success("You can download the refactored code as refactored_code.txt")
+
+    # Button to trigger code feedback
+    if st.button("Get Code Feedback") and code:
+        with st.spinner("Getting feedback on your code..."):
+            feedback = code_feedback(code)
+            st.subheader("Code Feedback:")
+            st.write(feedback)
+
+            # Ensure feedback is a string for download
+            feedback_text = feedback if isinstance(feedback, str) else str(feedback)
+
+            # Provide download option for code feedback
+            st.download_button(
+                label="Download Code Feedback",
+                data=feedback_text,  # Use the extracted string here
+                file_name="code_feedback.txt",
+                mime="text/plain",
+            )
+            st.success("You can download the code feedback as code_feedback.txt")
+
+    # Add button to suggest best practices
+    if st.button("Suggest Best Practices") and code:
+        with st.spinner("Getting best practices..."):
+            best_practices = suggest_best_practices(code)
+            st.subheader("Best Practices Suggestions:")
+            st.write(best_practices)
+
+            # Provide download option for best practices suggestions
+            best_practices_text = (
+                best_practices
+                if isinstance(best_practices, str)
+                else str(best_practices)
+            )
+            st.download_button(
+                label="Download Best Practices Suggestions",
+                data=best_practices_text,
+                file_name="best_practices.txt",
+                mime="text/plain",
+            )
+            st.success(
+                "You can download the best practices suggestions as best_practices.txt"
+            )
+
+    # Button to trigger error removal
+    if st.button("Remove Code Errors") and code:
+        with st.spinner("Removing errors from your code..."):
+            error_removal_suggestions = remove_code_errors(code)
+            st.subheader("Error Removal Suggestions:")
+            st.write(error_removal_suggestions)
+
+            # Provide download option for error removal suggestions
+            error_removal_text = (
+                error_removal_suggestions
+                if isinstance(error_removal_suggestions, str)
+                else str(error_removal_suggestions)
+            )
+            st.download_button(
+                label="Download Error Removal Suggestions",
+                data=error_removal_text,
+                file_name="error_removal_suggestions.txt",
+                mime="text/plain",
+            )
+            st.success(
+                "You can download the error removal suggestions as error_removal_suggestions.txt"
+            )
+
+
+if __name__ == "__main__":
+    main()

openai_client.py

@@ -0,0 +1,148 @@
+import os
+from dotenv import load_dotenv
+from openai import OpenAI
+import anthropic
+
+# Load environment variables from .env file
+load_dotenv()
+
+client = OpenAI(
+    api_key=os.getenv("OPENAI_API_KEY"),
+    base_url=os.getenv("OPENAI_API_BASE"),  # Uncomment if using a custom base URL
+)
+
+
+# Function to get GPT-4o Mini response
+def get_code_review_response(prompt, max_tokens=1000):
+    try:
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are an AI assistant who helps users in code reviews by deep thinking in points max 5-6 point shortly.",
+                },
+                {"role": "user", "content": prompt},
+            ],
+            max_tokens=max_tokens,
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        return "Sorry, an error occurred while generating your idea. Please try again later."
+
+
+# Function to refactor code
+def refactor_code(code_snippet):
+    try:
+        response = client.chat.completions.create(
+            model="gpt-4o-2024-08-06",
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are an expert code refactoring assistant.",
+                },
+                {
+                    "role": "user",
+                    "content": f"Refactor the following code. Do not provide any explanation or comments, just return the refactored code.\n{code_snippet}",
+                },
+            ],
+        )
+        refactored_code = response.choices[0].message.content
+        return refactored_code
+    except Exception as e:
+        return "Sorry, an error occurred while refactoring your code. Please try again later."
+
+
+# Initialize the Anthropic client
+anthropic_client = anthropic.Anthropic(api_key=os.getenv("ANTHROPIC_API_KEY"))
+
+
+# Function to get feedback on code using Anthropic
+def code_feedback(code_snippet):
+    try:
+        response = anthropic_client.messages.create(
+            model="claude-3-5-sonnet-20240620",
+            max_tokens=1024,
+            messages=[
+                {
+                    "role": "user",
+                    "content": f"Please provide feedback on the given code, don't refactor the code:\n{code_snippet}",
+                },
+            ],
+        )
+
+        # Extract feedback text from the response
+        feedback = response.text if hasattr(response, "text") else str(response)
+
+        # Check if feedback is a Message object and extract text if necessary
+        if hasattr(response, "content") and isinstance(response.content, list):
+            feedback = "\n\n".join(
+                [
+                    text_block.text
+                    for text_block in response.content
+                    if hasattr(text_block, "text")
+                ]
+            )
+
+        return feedback
+
+    except Exception as e:
+        return "Sorry, an error occurred while getting feedback on your code. Please try again later."
+
+
+# Function to suggest best coding practices based on given code
+def suggest_best_practices(code_snippet):
+    try:
+        response = anthropic_client.messages.create(
+            model="claude-3-5-sonnet-20240620",
+            max_tokens=1024,
+            messages=[
+                {
+                    "role": "user",
+                    "content": (
+                        f"Based on the following code, suggest best practices max 5-6 point shortly"
+                        f"for coding patterns that align with industry standards: \n{code_snippet}"
+                    ),
+                },
+            ],
+        )
+
+        # Extract suggestions from the response
+        best_practices = response.text if hasattr(response, "text") else str(response)
+
+        # Check if the feedback is a Message object and extract text if necessary
+        if hasattr(response, "content") and isinstance(response.content, list):
+            best_practices = "\n\n".join(
+                [
+                    text_block.text
+                    for text_block in response.content
+                    if hasattr(text_block, "text")
+                ]
+            )
+
+        return best_practices
+
+    except Exception as e:
+        return "Sorry, an error occurred while suggesting best practices. Please try again later."
+
+
+# Function to remove code errors
+def remove_code_errors(code_snippet):
+    try:
+        response = client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are an expert in debugging code. Provide concise suggestions to remove errors from the following code snippet.",
+                },
+                {
+                    "role": "user",
+                    "content": f"Identify and suggest fixes for errors in the following code:\n{code_snippet}",
+                },
+            ],
+        )
+        error_removal_suggestions = response.choices[0].message.content
+        return error_removal_suggestions
+    except Exception as e:
+        return "Sorry, an error occurred while removing code errors. Please try again later."