spiderforce4ai 2.4.9__tar.gz → 2.5.1__tar.gz

{spiderforce4ai-2.4.9 → spiderforce4ai-2.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: spiderforce4ai
-Version: 2.4.9
+Version: 2.5.1
 Summary: Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service with LLM post-processing
 Home-page: https://petertam.pro
 Author: Piotr Tamulewicz

{spiderforce4ai-2.4.9 → spiderforce4ai-2.5.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spiderforce4ai"
-version = "2.4.9"
+version = "2.5.1"
 description = "Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service with LLM post-processing"
 readme = "README.md"
 authors = [

{spiderforce4ai-2.4.9 → spiderforce4ai-2.5.1}/setup.py

@@ -7,7 +7,7 @@ with open("README.md", encoding="utf-8") as f:
 
 setup(
     name="spiderforce4ai",
-    version="2.4.9",
+    version="2.5.1",
     author="Piotr Tamulewicz",
     author_email="pt@petertam.pro",
     description="Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service with LLM post-processing",

{spiderforce4ai-2.4.9 → spiderforce4ai-2.5.1}/spiderforce4ai/__init__.py

@@ -5,6 +5,9 @@ import asyncio
 import aiohttp
 import json
 import logging
+
+logger = logging.getLogger(__name__)
+import logging
 from typing import List, Dict, Union, Optional, Tuple, Callable, Any
 from dataclasses import dataclass, asdict
 from urllib.parse import urljoin, urlparse
@@ -746,7 +749,8 @@ class SpiderForce4AI:
                     
                 for result in successful_results:
                     try:
-                        result.extraction_result = asyncio.run(agent.process_content(result.url, result.markdown))
+                        # Process content synchronously since it's not an async method
+                        result.extraction_result = agent.process_content(result.url, result.markdown)
                         progress.update(llm_task, advance=1)
                     except Exception as e:
                         console.print(f"[red]Error in post-extraction processing for {result.url}: {str(e)}[/red]")
@@ -877,7 +881,20 @@ class SpiderForce4AI:
                     
                     for result in successful_results:
                         try:
-                            result.extraction_result = asyncio.run(agent.process_content(result.url, result.markdown))
+                            # Get LLM response
+                            llm_response = agent.process_content(result.url, result.markdown)
+                            if llm_response:
+                                # Add URL to the response before transformation
+                                llm_response['url'] = result.url
+                                # Apply transformation if provided
+                                if config.post_agent_transformer_function:
+                                    try:
+                                        result.extraction_result = config.post_agent_transformer_function(llm_response)
+                                    except Exception as e:
+                                        logger.error(f"Transformer error for {result.url}: {str(e)}")
+                                        result.extraction_result = llm_response  # Use original response if transform fails
+                                else:
+                                    result.extraction_result = llm_response
                             progress.update(llm_task, advance=1)
                         except Exception as e:
                             console.print(f"[red]Error in post-extraction processing for {result.url}: {str(e)}[/red]")

{spiderforce4ai-2.4.9 → spiderforce4ai-2.5.1}/spiderforce4ai.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: spiderforce4ai
-Version: 2.4.9
+Version: 2.5.1
 Summary: Python wrapper for SpiderForce4AI HTML-to-Markdown conversion service with LLM post-processing
 Home-page: https://petertam.pro
 Author: Piotr Tamulewicz