Adds llm query bot example

examples/pr_review_bot/README.md

@@ -0,0 +1,126 @@
+# AI-Powered Pull Request Review Bot
+
+This example demonstrates how to use Codegen to create an intelligent PR review bot that analyzes code changes and their dependencies to provide comprehensive code reviews. The bot uses GPT-4 to generate contextual feedback based on modified code and its relationships.
+
+> [!NOTE]
+> This codemod helps development teams by providing automated, context-aware code reviews that consider both direct and indirect code dependencies.
+
+## How the PR Review Bot Works
+
+The script analyzes pull requests in several key steps:
+
+1. **Symbol Analysis**
+   ```python
+   modified_symbols = codebase.get_modified_symbols_in_pr(pr_number)
+   for symbol in modified_symbols:
+       deps = codebase.get_symbol_dependencies(symbol, max_depth=2)
+       rev_deps = codebase.get_symbol_dependents(symbol, max_depth=2)
+   ```
+   - Identifies modified symbols in the PR
+   - Analyzes dependencies up to 2 levels deep
+   - Tracks reverse dependencies (symbols that depend on changes)
+
+2. **Context Building**
+   ```python
+   context = {
+       "pr_title": pr.title,
+       "pr_body": pr.body,
+       "modified_symbols": [...],
+       "context_symbols": [...]
+   }
+   ```
+   - Gathers PR metadata
+   - Collects modified code content
+   - Includes relevant dependency context
+
+3. **AI Review Generation**
+   ```python
+   review = codebase.ai_client.llm_query_with_retry(
+       messages=[...],
+       model="gpt-4",
+       max_tokens=2000
+   )
+   ```
+   - Uses GPT-4 for analysis
+   - Generates comprehensive review feedback
+   - Considers full context of changes
+
+## Why This Makes Code Review Better
+
+1. **Context-Aware Analysis**
+   - Understands code dependencies
+   - Considers impact of changes
+   - Reviews code in proper context
+
+2. **Comprehensive Review**
+   - Analyzes direct modifications
+   - Evaluates dependency impact
+   - Suggests improvements
+
+3. **Consistent Feedback**
+   - Structured review format
+   - Thorough analysis every time
+   - Scalable review process
+
+## Review Output Format
+
+The bot provides structured feedback including:
+
+```
+1. Overall Assessment
+   - High-level review of changes
+   - Impact analysis
+
+2. Specific Code Feedback
+   - Detailed code comments
+   - Style suggestions
+   - Best practices
+
+3. Potential Issues
+   - Security concerns
+   - Performance impacts
+   - Edge cases
+
+4. Dependency Analysis
+   - Impact on dependent code
+   - Breaking changes
+   - Integration considerations
+
+```
+
+## Key Benefits to Note
+
+1. **Better Code Quality**
+   - Thorough code analysis
+   - Consistent review standards
+   - Early issue detection
+
+2. **Time Savings**
+   - Automated initial review
+   - Quick feedback loop
+   - Reduced review burden
+
+3. **Knowledge Sharing**
+   - Educational feedback
+   - Best practice suggestions
+   - Team learning
+
+
+## Configuration Options
+
+You can customize the review by:
+- Adjusting dependency depth
+- Modifying the AI prompt
+- Changing the review focus areas
+- Tuning the GPT-4 parameters
+
+## Learn More
+
+- [Codegen Documentation](https://docs.codegen.com)
+- [OpenAI API Documentation](https://platform.openai.com/docs/api-reference)
+- [GitHub API Documentation](https://docs.github.com/en/rest)
+- [Codegen llm integration](https://docs.codegen.com/building-with-codegen/calling-out-to-llms)
+
+## Contributing
+
+Feel free to submit issues and enhancement requests! Contributions to improve the review bot's capabilities are welcome. 

examples/pr_review_bot/run.py

@@ -0,0 +1,92 @@
+import codegen
+from codegen import Codebase
+from codegen.sdk.enums import ProgrammingLanguage
+from codegen.sdk.codebase.config import CodebaseConfig, GSFeatureFlags, Secrets
+import json
+
+github_token = "Your github token"
+open_ai_key = "your open ai key"
+pr_number = 0  # Your PR number must be an integer
+
+codegen.function("pr-review-bot")
+
+
+def run(codebase: Codebase):
+    context_symbols = set()
+
+    modified_symbols = codebase.get_modified_symbols_in_pr(pr_number)
+    for symbol in modified_symbols:
+        # Get direct dependencies
+        deps = codebase.get_symbol_dependencies(symbol, max_depth=2)
+        context_symbols.update(deps)
+
+        # Get reverse dependencies (symbols that depend on this one)
+        rev_deps = codebase.get_symbol_dependents(symbol, max_depth=2)
+        context_symbols.update(rev_deps)
+
+    # Prepare context for LLM
+    context = {
+        "modified_symbols": [
+            {
+                "name": symbol.name,
+                "type": symbol.symbol_type.value,
+                "filepath": symbol.filepath,
+                "content": symbol.content,
+            }
+            for symbol in modified_symbols
+        ],
+        "context_symbols": [
+            {
+                "name": symbol.name,
+                "type": symbol.symbol_type.value,
+                "filepath": symbol.filepath,
+                "content": symbol.content,
+            }
+            for symbol in context_symbols
+        ],
+    }
+
+    system_prompt = """
+    You are a helpful assistant that reviews pull requests and provides feedback on the code.
+    """
+    # Generate review using AI
+    prompt = f"""Please review this pull request based on the following context:
+
+Title: {context["pr_title"]}
+Description: {context["pr_body"]}
+
+Modified Symbols:
+{json.dumps(context["modified_symbols"], indent=2)}
+
+Related Context (Dependencies):
+{json.dumps(context["context_symbols"], indent=2)}
+
+Please provide a thorough code review that includes:
+1. Overall assessment
+2. Specific feedback on modified code
+3. Potential issues or improvements
+4. Impact on dependencies
+5. Suggestions for testing
+"""
+
+    review = codebase.ai_client.llm_query_with_retry(messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": prompt}], model="gpt-4", max_tokens=2000, temperature=0.7)
+    return review
+
+
+if __name__ == "__main__":
+    print("Starting codebase analysis...")
+    codebase = Codebase.from_repo(
+        "getsentry/sentry",
+        shallow=False,
+        programming_language=ProgrammingLanguage.PYTHON,
+        config=CodebaseConfig(
+            secrets=Secrets(openai_key=open_ai_key, github_api_key=github_token),
+            feature_flags=GSFeatureFlags(
+                sync_enabled=True,
+            ),
+        ),
+    )
+    review = run(codebase)
+    print(review)
+
+    print("Codebase analysis complete.")