Updated pathing for Wizards And Sorcery revised, migrated to poetry

README.md

@@ -9,7 +9,7 @@ app_file: app.py
 pinned: false
 ---
 
-# Retrieval Augmented Generation for Wizardsa & Wizardy Rule Sets
+# Retrieval Augmented Generation for Wizards & Wizardy Rule Sets
 
 ## Project Overview
 

app.py

@@ -19,7 +19,7 @@ def load_enhanced_json(file_path):
     with open(file_path, 'r') as file:
         return json.load(file)
 
-enhanced_json_file = "SwordsAndWizardry_enhanced_output.json"
+enhanced_json_file = "./output/SWCompleteRevisedPDF_enhanced_output.json"
 enhanced_data = load_enhanced_json(enhanced_json_file)
 
 # Extract document summary and page summaries
@@ -27,7 +27,7 @@ document_summary = enhanced_data.get('document_summary', 'No document summary av
 page_summaries = {int(page): data['summary'] for page, data in enhanced_data.get('pages', {}).items()}
 
 # Import saved file and view
-embeddings_df_save_path = "SwordsAndWizardry_output_embeddings.csv"
+embeddings_df_save_path = "./output/SWCompleteRevisedPDF_output_embeddings.csv"
 print("Loading embeddings.csv")
 text_chunks_and_embedding_df_load = pd.read_csv(embeddings_df_save_path)
 print("Embedding file loaded")

pyproject.toml

@@ -0,0 +1,21 @@
+[tool.poetry]
+name = "ruleslawyer"
+version = "0.1.0"
+description = "Ingest PDFs, process into a json, generate embeddings, and load into a chat interface for RAG."
+authors = ["Alan Meigs <alan.meigs@gmail.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+pandas = "^2.2.3"
+numpy = "^2.1.2"
+openai = "^1.53.0"
+gradio = "^5.4.0"
+sentence-transformers = "^3.2.1"
+torch = "^2.5.1"
+docling-core = "^2.3.1" # This may need to be updated to the correct version.
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"