, , and tags."
+ )
+ elif metrics["accuracy"] < 0.8:
feedback.append("ā
**Good Accuracy**: Most functions are found, but some are missed.")
feedback.append("Fine-tune the extraction logic for edge cases.")
else:
feedback.append("š **Excellent Accuracy**: Function extraction is working well!")
-
+
feedback.append("")
-
+
# Completeness feedback
- if metrics['completeness'] < 0.5:
+ if metrics["completeness"] < 0.5:
feedback.append("ā ļø **Low Completeness**: Not extracting enough functions overall.")
feedback.append("Increase the limit or improve the search scope.")
-
+
# Robustness feedback
- if metrics['robustness'] < 0.8:
+ if metrics["robustness"] < 0.8:
feedback.append("ā ļø **Low Robustness**: The scraper fails on some HTML formats.")
feedback.append("Add try-catch blocks and handle different documentation structures.")
feedback.append("Consider multiple parsing strategies and fallback methods.")
-
+
# Specific improvements
feedback.append("")
feedback.append("## Specific Improvements:")
-
+
# Analyze test case results
for key, value in artifacts.items():
- if key.startswith('test_case_') and isinstance(value, dict):
- if 'error' in key:
+ if key.startswith("test_case_") and isinstance(value, dict):
+ if "error" in key:
feedback.append(f"- Fix error in {key}: {value}")
- elif value.get('found_count', 0) < value.get('expected_count', 0):
- feedback.append(f"- Improve extraction for {key}: found {value.get('found_count', 0)}/{value.get('expected_count', 0)} functions")
-
+ elif value.get("found_count", 0) < value.get("expected_count", 0):
+ feedback.append(
+ f"- Improve extraction for {key}: found {value.get('found_count', 0)}/{value.get('expected_count', 0)} functions"
+ )
+
# Documentation URL hints (these will be fetched by readurls plugin)
feedback.append("")
feedback.append("## Documentation References:")
@@ -362,5 +367,5 @@ def generate_feedback(metrics: Dict[str, float], artifacts: Dict[str, Any]) -> s
feedback.append("- Python docs: https://docs.python.org/3/library/json.html")
feedback.append("- Requests docs: https://requests.readthedocs.io/en/latest/api/")
feedback.append("- BeautifulSoup docs: https://www.crummy.com/software/BeautifulSoup/bs4/doc/")
-
- return '\n'.join(feedback)
\ No newline at end of file
+
+ return "\n".join(feedback)
diff --git a/examples/web_scraper_optillm/initial_program.py b/examples/web_scraper_optillm/initial_program.py
index f0c97f5a2..4daead447 100644
--- a/examples/web_scraper_optillm/initial_program.py
+++ b/examples/web_scraper_optillm/initial_program.py
@@ -18,94 +18,102 @@
def scrape_api_docs(html_content: str) -> List[Dict[str, any]]:
"""
Extract API documentation from HTML content.
-
+
Args:
html_content: Raw HTML content of a documentation page
-
+
Returns:
List of dictionaries containing function documentation
"""
- soup = BeautifulSoup(html_content, 'html.parser')
+ soup = BeautifulSoup(html_content, "html.parser")
functions = []
-
+
# Try multiple approaches to find functions
# 1. Look for code blocks
- code_blocks = soup.find_all('code')
+ code_blocks = soup.find_all("code")
for block in code_blocks:
text = block.get_text(strip=True)
- if '(' in text and ')' in text:
- functions.append({
- 'name': text.split('(')[0].strip(),
- 'signature': text,
- 'description': 'No description found',
- 'parameters': extract_parameters(text)
- })
-
+ if "(" in text and ")" in text:
+ functions.append(
+ {
+ "name": text.split("(")[0].strip(),
+ "signature": text,
+ "description": "No description found",
+ "parameters": extract_parameters(text),
+ }
+ )
+
# 2. Look for function signatures in headers (h3)
- h3_blocks = soup.find_all('h3')
+ h3_blocks = soup.find_all("h3")
for block in h3_blocks:
text = block.get_text(strip=True)
- if '(' in text and ')' in text:
- functions.append({
- 'name': text.split('(')[0].strip(),
- 'signature': text,
- 'description': 'No description found',
- 'parameters': extract_parameters(text)
- })
-
+ if "(" in text and ")" in text:
+ functions.append(
+ {
+ "name": text.split("(")[0].strip(),
+ "signature": text,
+ "description": "No description found",
+ "parameters": extract_parameters(text),
+ }
+ )
+
# 3. Look for dt elements with sig class
- dt_blocks = soup.find_all('dt', class_='sig')
+ dt_blocks = soup.find_all("dt", class_="sig")
for block in dt_blocks:
- sig_name = block.find(class_='sig-name')
+ sig_name = block.find(class_="sig-name")
if sig_name:
name = sig_name.get_text(strip=True)
- functions.append({
- 'name': name,
- 'signature': block.get_text(strip=True),
- 'description': 'No description found',
- 'parameters': extract_parameters(block.get_text(strip=True))
- })
-
+ functions.append(
+ {
+ "name": name,
+ "signature": block.get_text(strip=True),
+ "description": "No description found",
+ "parameters": extract_parameters(block.get_text(strip=True)),
+ }
+ )
+
return functions[:20] # Return more functions
def extract_parameters(signature: str) -> List[Dict[str, str]]:
"""
Extract parameter information from a function signature.
-
+
Args:
signature: Function signature string
-
+
Returns:
List of parameter dictionaries
"""
params = []
# Very basic parameter extraction
- match = re.search(r'\((.*?)\)', signature)
+ match = re.search(r"\((.*?)\)", signature)
if match:
param_string = match.group(1)
if param_string:
- param_parts = param_string.split(',')
+ param_parts = param_string.split(",")
for part in param_parts:
part = part.strip()
if part:
- params.append({
- 'name': part.split('=')[0].strip(),
- 'type': 'unknown',
- 'default': None,
- 'description': ''
- })
-
+ params.append(
+ {
+ "name": part.split("=")[0].strip(),
+ "type": "unknown",
+ "default": None,
+ "description": "",
+ }
+ )
+
return params
def format_documentation(api_docs: List[Dict[str, any]]) -> str:
"""
Format extracted documentation into a readable string.
-
+
Args:
api_docs: List of API documentation dictionaries
-
+
Returns:
Formatted documentation string
"""
@@ -114,15 +122,17 @@ def format_documentation(api_docs: List[Dict[str, any]]) -> str:
output.append(f"Function: {doc['name']}")
output.append(f"Signature: {doc['signature']}")
output.append(f"Description: {doc['description']}")
-
- if doc.get('parameters'):
+
+ if doc.get("parameters"):
output.append("Parameters:")
- for param in doc['parameters']:
+ for param in doc["parameters"]:
output.append(f" - {param['name']}: {param.get('description', 'No description')}")
-
+
output.append("") # Empty line between functions
-
- return '\n'.join(output)
+
+ return "\n".join(output)
+
+
# EVOLVE-BLOCK-END
@@ -143,7 +153,7 @@ def format_documentation(api_docs: List[Dict[str, any]]) -> str: