Merge pull request #273 from JGalego/bugfix/bedrock-runs

bugfix: ScriptCreatorGraph verbose settings + RobotsNode handling model IDs

Author: VinciGit00

scrapegraphai/graphs/abstract_graph.py

@@ -49,19 +49,18 @@ def __init__(self, prompt: str, config: dict, source: Optional[str] = None):
         self.embedder_model = self._create_default_embedder(llm_config=config["llm"]
                                                             ) if "embeddings" not in config else self._create_embedder(
             config["embeddings"])
+        self.verbose = False if config is None else config.get(
+            "verbose", False)
+        self.headless = True if config is None else config.get(
+            "headless", True)
+        self.loader_kwargs = config.get("loader_kwargs", {})
 
         # Create the graph
         self.graph = self._create_graph()
         self.final_state = None
         self.execution_info = None
 
         # Set common configuration parameters
-        self.verbose = False if config is None else config.get(
-            "verbose", False)
-        self.headless = True if config is None else config.get(
-            "headless", True)
-        self.loader_kwargs = config.get("loader_kwargs", {})
-
         common_params = {"headless": self.headless,
                          "verbose": self.verbose,
                          "loader_kwargs": self.loader_kwargs,

scrapegraphai/nodes/robots_node.py

@@ -96,10 +96,11 @@ def execute(self, state: dict) -> dict:
             base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
             loader = AsyncChromiumLoader(f"{base_url}/robots.txt")
             document = loader.load()
-            if "ollama" in self.llm_model.model_name:
+            if hasattr(self.llm_model, "model_name") and "ollama" in self.llm_model.model_name:
                 self.llm_model.model_name = self.llm_model.model_name.split("/")[-1]
                 model = self.llm_model.model_name.split("/")[-1]
-
+            elif hasattr(self.llm_model, "model_id"):  # Bedrock uses model IDs, not model names
+                model = self.llm_model.model_id.split("/")[-1]
             else:
                 model = self.llm_model.model_name
             try: