from modules.config.categories import ScriptureCategoryConstants from modules.google_drive.google_drive_utils import convert_drive_url_to_direct kamba_ramayanam_config = { "name": "kamba_ramayanam", "title": "Kamba Ramayanam (Tamil)", "banner_url": convert_drive_url_to_direct( "https://drive.google.com/file/d/1_e4AKWZUP5eBuob0yWIZfnERnSWVdcJl/view?usp=drive_link" ), "category" : ScriptureCategoryConstants.ITHIHASAM, "output_dir": "./output/kamba_ramayanam", "collection_name": "kamba_ramayanam", "unit": "chunk", "unit_field": "chunk_index", # "field_mapping": { # "chapter_name": lambda doc: f"{doc.get('kandam','')}", # "title": lambda doc: f"{doc.get('padalam_ta','')} - {doc.get('padalam_en','')}".strip(), # "author": lambda doc: "Kamban", # "unit_index": "chunk_index", # "verse": lambda doc: int(doc.get("verse_number", "0")), # "relative_path": lambda doc: f"{doc.get('padalam_ta','')} - {doc.get('padalam_en','')}".strip(), # }, "metadata_fields": [ { "name": "chunk_index", "label": "Page Index", "datatype": "int", "description": "The index of the chunk", "show_as_filter": True, "is_unique": True, }, { "name": "filename", "label": "File name from the source", "datatype": "str", "description": "The name of the file.", }, ], "pdf_path": "./data/kamba_ramayanam.pdf", "source": "https://archive.org/details/vrajeshkumar_gmail_061/01-%E0%AE%AA%E0%AE%BE%E0%AE%B2%20%E0%AE%95%E0%AE%BE%E0%AE%A3%E0%AF%8D%E0%AE%9F%E0%AE%AE%E0%AF%8D/page/n15/mode/2up", "language": "tamil", "example_labels": [ "About Jatayu", "About Hanuman", "About Vali", "About Sita", "About Ravana", ], "examples": [ "What is the significance of Jatayu? show some sanskrit verses to support the argument", "Show some verses where Hanuman is mentioned", "How did Rama kill Vali", "How was Sita abducted", "How did Rama kill Ravana?", ], "llm_hints": [], }