diff --git a/scrapegraphai/graphs/pdf_scraper_graph.py b/scrapegraphai/graphs/pdf_scraper_graph.py index 10556213..912f141e 100644 --- a/scrapegraphai/graphs/pdf_scraper_graph.py +++ b/scrapegraphai/graphs/pdf_scraper_graph.py @@ -1,3 +1,4 @@ + """ PDFScraperGraph Module """ @@ -9,7 +10,6 @@ from .abstract_graph import AbstractGraph from ..nodes import ( FetchNode, - RAGNode, GenerateAnswerPDFNode ) @@ -63,14 +63,7 @@ class PDFScraperGraph(AbstractGraph): input='pdf | pdf_dir', output=["doc"], ) - rag_node = RAGNode( - input="user_prompt & doc", - output=["relevant_chunks"], - node_config={ - "llm_model": self.llm_model, - "embedder_model": self.embedder_model - } - ) + generate_answer_node_pdf = GenerateAnswerPDFNode( input="user_prompt & (relevant_chunks | doc)", output=["answer"], @@ -83,12 +76,10 @@ class PDFScraperGraph(AbstractGraph): return BaseGraph( nodes=[ fetch_node, - rag_node, generate_answer_node_pdf, ], edges=[ - (fetch_node, rag_node), - (rag_node, generate_answer_node_pdf) + (fetch_node, generate_answer_node_pdf) ], entry_point=fetch_node ) @@ -104,4 +95,4 @@ class PDFScraperGraph(AbstractGraph): inputs = {"user_prompt": self.prompt, self.input_key: self.source} self.final_state, self.execution_info = self.graph.execute(inputs) - return self.final_state.get("answer", "No answer found.") + return self.final_state.get("answer", "No answer found.") \ No newline at end of file diff --git a/scrapegraphai/graphs/smart_scraper_graph.py b/scrapegraphai/graphs/smart_scraper_graph.py index ee230695..aadd0887 100644 --- a/scrapegraphai/graphs/smart_scraper_graph.py +++ b/scrapegraphai/graphs/smart_scraper_graph.py @@ -117,4 +117,4 @@ class SmartScraperGraph(AbstractGraph): inputs = {"user_prompt": self.prompt, self.input_key: self.source} self.final_state, self.execution_info = self.graph.execute(inputs) - return self.final_state.get("answer", "No answer found.") \ No newline at end of file + return self.final_state.get("answer", "No answer found.") diff --git a/scrapegraphai/nodes/generate_answer_pdf_node.py b/scrapegraphai/nodes/generate_answer_pdf_node.py index 3a520745..1f468a55 100644 --- a/scrapegraphai/nodes/generate_answer_pdf_node.py +++ b/scrapegraphai/nodes/generate_answer_pdf_node.py @@ -95,9 +95,7 @@ class GenerateAnswerPDFNode(BaseNode): output_parser = JsonOutputParser() format_instructions = output_parser.get_format_instructions() - chains_dict = {} - # Use tqdm to add progress bar for i, chunk in enumerate( tqdm(doc, desc="Processing chunks", disable=not self.verbose) @@ -107,7 +105,7 @@ class GenerateAnswerPDFNode(BaseNode): template=template_no_chunks_pdf, input_variables=["question"], partial_variables={ - "context": chunk.page_content, + "context":chunk, "format_instructions": format_instructions, }, ) @@ -116,7 +114,7 @@ class GenerateAnswerPDFNode(BaseNode): template=template_chunks_pdf, input_variables=["question"], partial_variables={ - "context": chunk.page_content, + "context":chunk, "chunk_id": i + 1, "format_instructions": format_instructions, },