langroid 0.58.0__tar.gz → 0.58.2__tar.gz

{langroid-0.58.0 → langroid-0.58.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langroid
-Version: 0.58.0
+Version: 0.58.2
 Summary: Harness LLMs with Multi-Agent Programming
 Author-email: Prasad Chalasani <pchalasani@gmail.com>
 License: MIT
@@ -94,8 +94,8 @@ Requires-Dist: chainlit<3.0.0,>=2.0.1; extra == 'chainlit'
 Requires-Dist: python-socketio<6.0.0,>=5.11.0; extra == 'chainlit'
 Provides-Extra: chromadb
 Requires-Dist: chromadb<=0.4.23,>=0.4.21; extra == 'chromadb'
-Provides-Extra: crawl-4-ai
-Requires-Dist: crawl4ai>=0.6.3; extra == 'crawl-4-ai'
+Provides-Extra: crawl4ai
+Requires-Dist: crawl4ai>=0.6.3; extra == 'crawl4ai'
 Provides-Extra: db
 Requires-Dist: psycopg2-binary>=2.9.10; extra == 'db'
 Requires-Dist: psycopg2<3.0.0,>=2.9.7; extra == 'db'
@@ -347,6 +347,8 @@ teacher_task.run()
 <summary> <b>Click to expand</b></summary>
 
 - **Jul 2025:**
+  - [0.58.0](https://github.com/langroid/langroid/releases/tag/0.58.0) Crawl4AI integration - 
+    browser-based web crawling with Playwright for JavaScript-heavy sites, no API key required (thank you @abab-dev!).
   - [0.57.0](https://github.com/langroid/langroid/releases/tag/0.57.0) HTML Logger for interactive task visualization - 
     self-contained HTML logs with collapsible entries, auto-refresh, and persistent UI state.
 - **Jun 2025:**

{langroid-0.58.0 → langroid-0.58.2}/README.md

@@ -144,6 +144,8 @@ teacher_task.run()
 <summary> <b>Click to expand</b></summary>
 
 - **Jul 2025:**
+  - [0.58.0](https://github.com/langroid/langroid/releases/tag/0.58.0) Crawl4AI integration - 
+    browser-based web crawling with Playwright for JavaScript-heavy sites, no API key required (thank you @abab-dev!).
   - [0.57.0](https://github.com/langroid/langroid/releases/tag/0.57.0) HTML Logger for interactive task visualization - 
     self-contained HTML logs with collapsible entries, auto-refresh, and persistent UI state.
 - **Jun 2025:**

{langroid-0.58.0 → langroid-0.58.2}/langroid/parsing/url_loader.py

@@ -25,7 +25,7 @@ if TYPE_CHECKING:
         from crawl4ai.extraction_strategy import ExtractionStrategy
         from crawl4ai.markdown_generation_strategy import MarkdownGenerationStrategy
     except ImportError:
-        raise LangroidImportError("crawl4ai", "crawl-4-ai")
+        raise LangroidImportError("crawl4ai", "crawl4ai")
 
 load_dotenv()
 
@@ -70,48 +70,58 @@ class ExaCrawlerConfig(BaseCrawlerConfig):
         env_prefix = "EXA_"
 
 
-def _resolve_crawl4ai_forward_refs(cls: Any) -> Any:
-    """
-    A class decorator that resolves forward references for fields in a Pydantic
-    model that depend on the optional 'crawl4ai' library.
-    """
-    try:
-        from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig  # noqa: F401
-        from crawl4ai.content_scraping_strategy import (  # noqa: F401
-            ContentScrapingStrategy,
-        )
-        from crawl4ai.deep_crawling import DeepCrawlStrategy  # noqa: F401
-        from crawl4ai.extraction_strategy import ExtractionStrategy  # noqa: F401
-        from crawl4ai.markdown_generation_strategy import (  # noqa: F401
-            MarkdownGenerationStrategy,
-        )
-
-        #  Create a namespace dictionary from locals() but exclude 'cls'.
-        # This prevents the TypeError.
-        namespace = {name: value for name, value in locals().items() if name != "cls"}
-        cls.update_forward_refs(**namespace)
-
-    except ImportError:
-        # If crawl4ai is not installed, do nothing.
-        pass
-    return cls
-
-
-@_resolve_crawl4ai_forward_refs
 class Crawl4aiConfig(BaseCrawlerConfig):
-    """
-    Configuration for the Crawl4aiCrawler.
-    """
+    """Configuration for the Crawl4aiCrawler."""
 
     crawl_mode: Literal["simple", "deep"] = "simple"
     extraction_strategy: Optional["ExtractionStrategy"] = None
     markdown_strategy: Optional["MarkdownGenerationStrategy"] = None
     deep_crawl_strategy: Optional["DeepCrawlStrategy"] = None
     scraping_strategy: Optional["ContentScrapingStrategy"] = None
-
     browser_config: Optional["BrowserConfig"] = None
     run_config: Optional["CrawlerRunConfig"] = None
 
+    _refs_resolved: bool = False
+
+    def __init_subclass__(cls, **kwargs: Any) -> None:
+        """Resolve forward references when class is first subclassed or instantiated."""
+        super().__init_subclass__(**kwargs)
+        cls._resolve_forward_refs()
+
+    @classmethod
+    def _resolve_forward_refs(cls) -> None:
+        """Resolve forward references only when needed."""
+        if not cls._refs_resolved:
+            try:
+                from crawl4ai.async_configs import BrowserConfig, CrawlerRunConfig
+                from crawl4ai.content_scraping_strategy import ContentScrapingStrategy
+                from crawl4ai.deep_crawling import DeepCrawlStrategy
+                from crawl4ai.extraction_strategy import ExtractionStrategy
+                from crawl4ai.markdown_generation_strategy import (
+                    MarkdownGenerationStrategy,
+                )
+
+                # Create namespace for update_forward_refs
+                namespace = {
+                    "BrowserConfig": BrowserConfig,
+                    "CrawlerRunConfig": CrawlerRunConfig,
+                    "ContentScrapingStrategy": ContentScrapingStrategy,
+                    "DeepCrawlStrategy": DeepCrawlStrategy,
+                    "ExtractionStrategy": ExtractionStrategy,
+                    "MarkdownGenerationStrategy": MarkdownGenerationStrategy,
+                }
+
+                cls.update_forward_refs(**namespace)
+                cls._refs_resolved = True
+            except ImportError:
+                # If crawl4ai is not installed, leave forward refs as strings
+                pass
+
+    def __init__(self, **kwargs: Any) -> None:
+        """Initialize and ensure forward refs are resolved."""
+        self._resolve_forward_refs()
+        super().__init__(**kwargs)
+
     class Config:
         arbitrary_types_allowed = True
 

{langroid-0.58.0 → langroid-0.58.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langroid"
-version = "0.58.0"
+version = "0.58.2"
 authors = [
     {name = "Prasad Chalasani", email = "pchalasani@gmail.com"},
 ]
@@ -270,7 +270,7 @@ asyncio = [
 firecrawl = [
     "firecrawl-py>=1.13.5",
 ]
-crawl-4-ai = [
+crawl4ai = [
     "crawl4ai>=0.6.3",
 ]