working speech graph with rag

examples/graph_examples/graph_evaluation_example.py

@@ -4,7 +4,6 @@ Module for evaluating the graph
 import os
 from scrapegraphai.evaluators import TrulensEvaluator
 from dotenv import load_dotenv
-import pandas as pd
 
 load_dotenv()
 
@@ -19,9 +18,9 @@ llm_config = {
 list_of_inputs = [
     ("List me all the titles and project descriptions",
      "https://perinim.github.io/projects/", llm_config),
-    ("Who is the author of the project?",
-     "https://perinim.github.io/projects/", llm_config),
-    ("What is the project about?", "https://perinim.github.io/projects/", llm_config)
+    # ("Who is the author of the project?",
+    #  "https://perinim.github.io/projects/", llm_config),
+    # ("What is the project about?", "https://perinim.github.io/projects/", llm_config),
 ]
 
 # Create the TrulensEvaluator instance
@@ -29,5 +28,4 @@ trulens_evaluator = TrulensEvaluator(openai_key)
 # Evaluate SmartScraperGraph on the list of inputs
 (results_df, answer) = trulens_evaluator.evaluate(list_of_inputs, dashboard=False)
 
-# Print the results
 print(answer)

examples/graph_examples/smart_scraper_example.py

@@ -17,7 +17,7 @@ llm_config = {
 
 # Define URL and PROMPT
 URL = "https://perinim.github.io/projects/"
-PROMPT = "List me all the titles and project descriptions"
+PROMPT = "List me all the titles and project descriptions and give me an audio"
 
 # Create the SmartScraperGraph instance
 smart_scraper_graph = SmartScraperGraph(PROMPT, URL, llm_config)

examples/graph_examples/speech_summary_graph_example.py

@@ -18,9 +18,9 @@ llm_config = {
 curr_dir = os.path.dirname(os.path.realpath(__file__))
 output_file_path = os.path.join(curr_dir, "website_summary.mp3")
 
-speech_summary_graph = SpeechSummaryGraph("""Make a summary of the webpage to be
+speech_summary_graph = SpeechSummaryGraph("""Make a summary of the news to be
 converted to audio for blind people.""",
-                                          "https://perinim.github.io/projects/", llm_config,
+                                          "https://www.wired.com/category/science/", llm_config,
                                           output_file_path)
 
 final_state = speech_summary_graph.run()

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "scrapegraphai"
-version = "0.0.6"
+version = "0.0.6-alpha"
 description = "A web scraping library based on LangChain which uses LLM and direct graph logic to create scraping pipelines."
 authors = [
     "Marco Vinciguerra <mvincig11@gmail.com>",

scrapegraphai/graphs/speech_summary_graph.py

@@ -6,10 +6,8 @@ from ..models import OpenAI, OpenAITextToSpeech
 from .base_graph import BaseGraph
 from ..nodes import (
     FetchHTMLNode,
-    ConditionalNode,
-    GetProbableTagsNode,
+    RAGNode,
     GenerateAnswerNode,
-    ParseHTMLNode,
     TextToSpeechNode,
 )
 
@@ -36,7 +34,7 @@ class SpeechSummaryGraph:
         output_path (str): The file path where the generated MP3 should be saved.
     """
 
-    def __init__(self, prompt: str, url: str, llm_config: dict, output_path: str):
+    def __init__(self, prompt: str, url: str, llm_config: dict, output_path: str = "website_summary.mp3"):
         """
         Initializes the SmartScraper with a prompt, URL, and language model configuration.
         """
@@ -80,28 +78,21 @@ class SpeechSummaryGraph:
             BaseGraph: An instance of the BaseGraph class.
         """
         fetch_html_node = FetchHTMLNode("fetch_html")
-        get_probable_tags_node = GetProbableTagsNode(
-            self.llm, "get_probable_tags")
-        parse_document_node = ParseHTMLNode("parse_document")
+        rag_node = RAGNode(self.llm, "rag")
         generate_answer_node = GenerateAnswerNode(self.llm, "generate_answer")
-        conditional_node = ConditionalNode(
-            "conditional", [parse_document_node, generate_answer_node])
         text_to_speech_node = TextToSpeechNode(
             self.text_to_speech_model, "text_to_speech")
 
         return BaseGraph(
             nodes={
                 fetch_html_node,
-                get_probable_tags_node,
-                conditional_node,
-                parse_document_node,
+                rag_node,
                 generate_answer_node,
                 text_to_speech_node
             },
             edges={
-                (fetch_html_node, get_probable_tags_node),
-                (get_probable_tags_node, conditional_node),
-                (parse_document_node, generate_answer_node),
+                (fetch_html_node, rag_node),
+                (rag_node, generate_answer_node),
                 (generate_answer_node, text_to_speech_node)
             },
             entry_point=fetch_html_node