Upload 7 files

.env

@@ -0,0 +1,3 @@
+GROQ_API_KEY="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"
+LANGCHAIN_API_KEY="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"
+LANGSMITH_PROJECT="AI Code Reviewer"

.gitignore

@@ -0,0 +1,2 @@
+venv/
+.env

READme.md

@@ -0,0 +1,32 @@
+## 🤖 AI Code Reviewer 📝
+
+🚀 Overview
+
+AI Code Reviewer is a Python-based application that leverages FastAPI and Streamlit to provide instant feedback on Python code. The app integrates LangChain and Groq's LLM (Gemma2-9b-it) to analyze code snippets, detect potential issues, and suggest improvements.
+
+🛠 Features
+
+🔍 Instant Code Review: Get feedback on Python code, including error detection and fixes.
+
+💡 Bug Detection: Identifies common mistakes like indentation errors and division by zero.
+
+🎯 Corrected Code Suggestions: Provides corrected versions of problematic code snippets.
+
+🚀 FastAPI Backend: A lightweight, high-performance API for processing requests.
+
+🌐 Streamlit Frontend: User-friendly web interface for easy interaction.
+
+🏗️ Tech Stack
+
+Python 3.11
+
+FastAPI (Backend API)
+
+Streamlit (Frontend UI)
+
+LangChain (LLM-based processing)
+
+Groq LLM (Gemma2-9b-it for language understanding)
+
+Uvicorn (ASGI server)
+

Research/Ai.ipynb

@@ -0,0 +1,238 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "##  AI Code Reviewer with Langchain and Groq"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "load_dotenv()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_groq import ChatGroq \n",
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.chains import LLMChain\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os \n",
+    "os.environ[\"GROQ_API_KEY\"]=os.getenv(\"GROQ_API_KEY\")\n",
+    "os.environ[\"LANGSMITH_TRACING_V2\"]=\"true\"\n",
+    "os.environ[\"LANGSMITH_ENDPOINT\"]=\"https://api.smith.langchain.com\"\n",
+    "os.environ[\"LANGCHAIN_API_KEY\"]=os.getenv(\"LANGCHAIN_API_KEY\")\n",
+    "os.environ[\"LANGSMITH_PROJECT\"]=\"AI Code Reviewer\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Loading The Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "GROQ_API_KEY=os.getenv(\"GROQ_API_KEY\")\n",
+    "llm=ChatGroq(api_key=GROQ_API_KEY,model_name=\"gemma2-9b-it\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response=llm.invoke(\"import numy as np\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'It seems like you\\'re trying to import the NumPy library. \\n\\nHowever, there\\'s a slight typo in your code.  \"numy\" should be \"numpy\".\\n\\nHere\\'s the corrected import statement:\\n\\n```python\\nimport numpy as np\\n```\\n\\nThis line of code imports the NumPy library and gives it the alias \"np\". This is a common convention in Python, allowing you to use \"np\" instead of writing out \"numpy\" every time you need to use a NumPy function or object.\\n\\n\\n\\nLet me know if you have any other questions or need help with NumPy!\\n'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "response.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Trying out with Different Prompts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import FewShotPromptTemplate, PromptTemplate\n",
+    "\n",
+    "# Define example responses for few-shot prompting\n",
+    "examples = [\n",
+    "    {\n",
+    "        \"input\": \"def add(a, b):\\nreturn a + b\",\n",
+    "        \"output\": \"Your function 'add' is missing proper indentation. Here's a corrected version:\\n\\ndef add(a, b):\\n    return a + b\\n\"\n",
+    "    },\n",
+    "    {\n",
+    "        \"input\": \"def divide(a, b):\\n    return a / b\",\n",
+    "        \"output\": \"Potential bug detected: Division by zero error. You should handle this case:\\n\\ndef divide(a, b):\\n    if b == 0:\\n        return 'Error: Division by zero'\\n    return a / b\\n\"\n",
+    "    }\n",
+    "]\n",
+    "\n",
+    "# Define example template\n",
+    "example_template = PromptTemplate(\n",
+    "    input_variables=[\"input\", \"output\"],\n",
+    "    template=\"Code: \\n{input}\\n\\nFeedback:\\n{output}\\n\"\n",
+    ")\n",
+    "prefix=\"\"\"You are a highly skilled Python code reviewer. \n",
+    "Your task is to analyze the given Python code, identify potential bugs, suggest improvements, and provide a corrected version of the code if necessary. Ensure that your feedback is clear, precise, and actionable.\n",
+    "First you have to specify where and what the error is.\n",
+    "Next give the correct code\n",
+    "\n",
+    "\"\"\"\n",
+    "\n",
+    "# Create a few-shot prompt template\n",
+    "few_shot_prompt = FewShotPromptTemplate(\n",
+    "    examples=examples,\n",
+    "    example_prompt=example_template,\n",
+    "    prefix=prefix,\n",
+    "    suffix=\"Code:\\n{input}\\n\\nFeedback:\",\n",
+    "    input_variables=[\"input\"]\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\saipr\\AppData\\Local\\Temp\\ipykernel_28632\\3821535042.py:2: LangChainDeprecationWarning: The class `LLMChain` was deprecated in LangChain 0.1.17 and will be removed in 1.0. Use :meth:`~RunnableSequence, e.g., `prompt | llm`` instead.\n",
+      "  llm_chain = LLMChain(llm=llm, prompt=few_shot_prompt)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create the LLMChain\n",
+    "llm_chain = LLMChain(llm=llm, prompt=few_shot_prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\saipr\\AppData\\Local\\Temp\\ipykernel_28632\\911030789.py:3: LangChainDeprecationWarning: The method `Chain.run` was deprecated in langchain 0.1.0 and will be removed in 1.0. Use :meth:`~invoke` instead.\n",
+      "  response = llm_chain.run(input=code_snippet)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The error is a simple typo. \n",
+      "\n",
+      "`nump` should be `numpy`. \n",
+      "\n",
+      "Here's the corrected code:\n",
+      "\n",
+      "```python\n",
+      "import numpy as np\n",
+      "``` \n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "# Example usage\n",
+    "code_snippet = \"import nump as np\"\n",
+    "response = llm_chain.run(input=code_snippet)\n",
+    "print(response)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

app.py

@@ -0,0 +1,62 @@
+import os
+import streamlit as st
+from langchain.prompts import FewShotPromptTemplate, PromptTemplate
+from langchain.chains import LLMChain
+from langchain_groq import ChatGroq
+from dotenv import load_dotenv
+load_dotenv()
+# Set up API key
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+llm = ChatGroq(api_key=GROQ_API_KEY, model_name="gemma2-9b-it")
+
+
+# Define example responses for few-shot prompting
+examples = [
+    {
+        "input": "def add(a, b):\nreturn a + b",
+        "output": "Your function 'add' is missing proper indentation. Here's a corrected version:\n\ndef add(a, b):\n    return a + b\n"
+    },
+    {
+        "input": "def divide(a, b):\n    return a / b",
+        "output": "Potential bug detected: Division by zero error. You should handle this case:\n\ndef divide(a, b):\n    if b == 0:\n        return 'Error: Division by zero'\n    return a / b\n"
+    }
+]
+
+# Define example template
+example_template = PromptTemplate(
+    input_variables=["input", "output"],
+    template="Code: \n{input}\n\nFeedback:\n{output}\n"
+)
+prefix="""You are a highly skilled Python code reviewer. 
+Your task is to analyze the given Python code, identify potential bugs, suggest improvements, and provide a corrected version of the code if necessary. Ensure that your feedback is clear, precise, and actionable.
+First you have to specify where and what the error is.
+Next give the correct code
+If the code is out of context replay "Out of Context"
+
+"""
+
+# Create a few-shot prompt template
+few_shot_prompt = FewShotPromptTemplate(
+    examples=examples,
+    example_prompt=example_template,
+    prefix=prefix,
+    suffix="Code:\n{input}\n\nFeedback:",
+    input_variables=["input"]
+)
+
+# Create the LLMChain
+llm_chain = LLMChain(llm=llm, prompt=few_shot_prompt)
+
+# Streamlit App
+st.title("🤖 AI Code Reviewer 📝")
+st.markdown("### Get instant feedback on your Python code! 🚀")
+
+code_snippet = st.text_area("✍️ Enter Python code below:", height=200)
+
+if st.button("🔍 Review Code"):
+    if code_snippet.strip():
+        response = llm_chain.run(input=code_snippet)
+        st.subheader("🧐 Review Feedback:")
+        st.code(response, language="python")
+    else:
+        st.warning("⚠️ Please enter some Python code to review!")

main.py

@@ -0,0 +1,88 @@
+import os
+import streamlit as st
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from langchain.prompts import FewShotPromptTemplate, PromptTemplate
+from langchain.chains import LLMChain
+from langchain_groq import ChatGroq
+import uvicorn
+
+# Load environment variables
+load_dotenv()
+
+# Set up API key
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+
+if not GROQ_API_KEY:
+    raise ValueError("🚨 API Key Missing! Please check your .env file and restart the app.")
+
+llm = ChatGroq(api_key=GROQ_API_KEY, model_name="gemma2-9b-it")
+
+# Define example responses for few-shot prompting
+examples = [
+    {
+        "input": "def add(a, b):\nreturn a + b",
+        "output": "Your function 'add' is missing proper indentation. Here's a corrected version:\n\ndef add(a, b):\n    return a + b\n"
+    },
+    {
+        "input": "def divide(a, b):\n    return a / b",
+        "output": "Potential bug detected: Division by zero error. You should handle this case:\n\ndef divide(a, b):\n    if b == 0:\n        return 'Error: Division by zero'\n    return a / b\n"
+    }
+]
+
+# Define example template
+example_template = PromptTemplate(
+    input_variables=["input", "output"],
+    template="Code: \n{input}\n\nFeedback:\n{output}\n"
+)
+prefix="""You are a highly skilled Python code reviewer. 
+Your task is to analyze the given Python code, identify potential bugs, suggest improvements, and provide a corrected version of the code if necessary. Ensure that your feedback is clear, precise, and actionable.
+First you have to specify where and what the error is.
+Next give the correct code
+If the code is out of context replay "Out of Context"
+
+"""
+
+# Create a few-shot prompt template
+few_shot_prompt = FewShotPromptTemplate(
+    examples=examples,
+    example_prompt=example_template,
+    prefix=prefix,
+    suffix="Code:\n{input}\n\nFeedback:",
+    input_variables=["input"]
+)
+
+# Create the LLMChain
+llm_chain = LLMChain(llm=llm, prompt=few_shot_prompt)
+
+# FastAPI Backend
+app = FastAPI()
+
+class CodeReviewRequest(BaseModel):
+    code: str
+
+@app.post("/review")
+def review_code(request: CodeReviewRequest):
+    if not request.code.strip():
+        raise HTTPException(status_code=400, detail="No code provided.")
+    response = llm_chain.run(input=request.code)
+    return {"feedback": response}
+
+# Streamlit Frontend
+st.title("🤖 AI Code Reviewer 📝")
+st.markdown("### Get instant feedback on your Python code! 🚀")
+
+code_snippet = st.text_area("✍️ Paste your Python code below:", height=200)
+
+if st.button("🔍 Review Code"):
+    if code_snippet.strip():
+        response = llm_chain.run(input=code_snippet)
+        st.subheader("🧐 Review Feedback:")
+        st.code(response, language="python")
+    else:
+        st.warning("⚠️ Please enter some Python code to review!")
+
+# Run FastAPI backend (for local testing)
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8001)

requirements.txt

@@ -0,0 +1,9 @@
+langchain
+langchain-community
+langchain-groq
+python-dotenv
+fastapi
+streamlit
+langsmith
+langserve
+uvicorn