ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: Move the checking of protocol and prepending protocol inside api handlers

Browse Source
This commit is contained in:
Aravind Karnam
2025-03-14 09:39:10 +05:30
parent cbb8755972
commit a3954dd4c6
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
deploy/docker/api.py
View File

@@ -48,6 +48,8 @@ async def handle_llm_qa(
) -> str: ) -> str:
"""Process QA using LLM with crawled content as context.""" """Process QA using LLM with crawled content as context."""
try: try:
if not url.startswith(('http://', 'https://')):
url = 'https://' + url
# Extract base URL by finding last '?q=' occurrence # Extract base URL by finding last '?q=' occurrence
last_q_index = url.rfind('?q=') last_q_index = url.rfind('?q=')
if last_q_index != -1: if last_q_index != -1:
@@ -61,7 +63,7 @@ async def handle_llm_qa(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
detail=result.error_message detail=result.error_message
) )
content = result.markdown.fit_markdown content = result.markdown.fit_markdown or result.markdown.raw_markdown
# Create prompt and get LLM response # Create prompt and get LLM response
prompt = f"""Use the following content as context to answer the question. prompt = f"""Use the following content as context to answer the question.
@@ -377,6 +379,7 @@ async def handle_crawl_request(
) -> dict: ) -> dict:
"""Handle non-streaming crawl requests.""" """Handle non-streaming crawl requests."""
try: try:
urls = [('https://' + url) if not url.startswith(('http://', 'https://')) else url for url in urls]
browser_config = BrowserConfig.load(browser_config) browser_config = BrowserConfig.load(browser_config)
crawler_config = CrawlerRunConfig.load(crawler_config) crawler_config = CrawlerRunConfig.load(crawler_config)