Merge pull request #429 from ScrapeGraphAI/421-default-prompt-template-customization

421 default prompt template customization

Author: VinciGit00

examples/extras/custom_prompt.py

@@ -0,0 +1,50 @@
+""" 
+Basic example of scraping pipeline using SmartScraper
+"""
+import os
+import json
+from dotenv import load_dotenv
+from scrapegraphai.graphs import SmartScraperGraph
+from scrapegraphai.utils import prettify_exec_info
+
+load_dotenv()
+
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+openai_key = os.getenv("OPENAI_APIKEY")
+
+prompt = "Some more info"
+
+graph_config = {
+    "llm": {
+        "api_key": openai_key,
+        "model": "gpt-3.5-turbo",
+    },
+    "additional_info": prompt,
+    "verbose": True,
+    "headless": False,
+}
+
+# ************************************************
+# Create the SmartScraperGraph instance and run it
+# ************************************************
+
+smart_scraper_graph = SmartScraperGraph(
+    prompt="List me all the projects with their description",
+    # also accepts a string with the already downloaded HTML code
+    source="https://perinim.github.io/projects/",
+    config=graph_config,
+)
+
+result = smart_scraper_graph.run()
+print(json.dumps(result, indent=4))
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = smart_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))

scrapegraphai/graphs/csv_scraper_graph.py

@@ -50,6 +50,7 @@ def _create_graph(self):
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema,
             }
         )

scrapegraphai/graphs/deep_scraper_graph.py

@@ -95,6 +95,7 @@ def _create_repeated_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema
             }
         )

scrapegraphai/graphs/json_scraper_graph.py

@@ -75,6 +75,7 @@ def _create_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema
             }
         )

scrapegraphai/graphs/markdown_scraper_graph.py

@@ -76,6 +76,7 @@ def _create_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema,
             }
         )

scrapegraphai/graphs/omni_scraper_graph.py

@@ -18,7 +18,6 @@
 
 from ..models import OpenAIImageToText
 
-
 class OmniScraperGraph(AbstractGraph):
     """
     OmniScraper is a scraping pipeline that automates the process of 
@@ -60,7 +59,6 @@ def __init__(self, prompt: str, source: str, config: dict, schema: Optional[Base
         super().__init__(prompt, config, source, schema)
 
         self.input_key = "url" if source.startswith("http") else "local_dir"
-        
 
     def _create_graph(self) -> BaseGraph:
         """
@@ -104,6 +102,7 @@ def _create_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema
             }
         )

scrapegraphai/graphs/pdf_scraper_graph.py

@@ -89,6 +89,7 @@ def _create_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema
             }
         )

scrapegraphai/graphs/script_creator_graph.py

@@ -84,6 +84,7 @@ def _create_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema,
             },
             library=self.library,

scrapegraphai/graphs/smart_scraper_graph.py

@@ -91,6 +91,7 @@ def _create_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema,
             }
         )

scrapegraphai/graphs/speech_graph.py

@@ -84,6 +84,7 @@ def _create_graph(self) -> BaseGraph:
             output=["answer"],
             node_config={
                 "llm_model": self.llm_model,
+                "additional_info": self.config.get("additional_info"),
                 "schema": self.schema
             }
         )