Upload folder using huggingface_hub

config.py

@@ -1143,6 +1143,87 @@ class SanatanConfig:
             ],
             "llm_hints": [],
         },        
+        {
+            "name": "katakam",
+            "title": "Katakam",
+            "output_dir": "./output/katakam",
+            "collection_name": "katakam",
+            "collection_embedding_fn": "openai",
+            "unit": "panchadhi",
+            "unit_field": "panchadhi",
+            # "chapter_order": lambda: get_chapter_order_from_katakam(),
+            "field_mapping": {
+                "text": "sanskrit",
+                "unit_index": "panchadhi",
+                "transliteration": "transliteration",
+                "chapter_name": lambda doc: (
+                    doc.get("prapaatakam_name")
+                    if doc.get("prapaatakam_name") and doc.get("prapaatakam_name") != "-"
+                    else "॥ काठकम् ॥"
+                ),
+                "relative_path": lambda doc: (
+                    "-"
+                    if not doc.get("panchadhi") or doc.get("panchadhi") == "-"
+                    else f"{doc.get('prapaatakam')}.{doc.get('anuvakam')}.{doc.get('panchadhi_index')} || {doc.get('panchadhi_sa')} ||"
+                ),
+            },
+            "metadata_fields": [
+                {
+                    "name": "prapaatakam",
+                    "datatype": "int",
+                    "label": "Prapaatakam Number",
+                    "description": "Prapaatakam Number",
+                    "show_as_filter": True,
+                    "is_unique": True,
+                },
+                {
+                    "name": "anuvakam",
+                    "datatype": "int",
+                    "label": "Anuvakam Number",
+                    "description": "Anuvakam Number",
+                    "show_as_filter": True,
+                    "is_unique": True,
+                },
+                {
+                    "name": "panchadhi_index",
+                    "datatype": "int",
+                    "label": "Relative Panchadhi Number",
+                    "description": "Relative Panchadhi Number",
+                    "show_as_filter": True,
+                    "is_unique": True,
+                },
+                {
+                    "name": "panchadhi",
+                    "datatype": "int",
+                    "label": "Absolute Panchadhi Number",
+                    "description": "Absolute Panchadhi Number",
+                    "show_as_filter": True,
+                    "is_unique": True,
+                },
+                {
+                    "name": "sanskrit",
+                    "label": "Lyrics in sanskrit",
+                    "datatype": "str",
+                    "description": "The original sloka in sanskrit.",
+                },
+                {
+                    "name": "transliteration",
+                    "label": "Transliteration in english",
+                    "datatype": "str",
+                    "description": "The original sloka transliterated in English.",
+                },
+            ],
+            "pdf_path": "./data/katakam.pdf",
+            "source": "https://sanskritdocuments.org/doc_veda/taittirIyabrAhmaNam.html",
+            "language": "san+eng",
+            "example_labels": [
+                "Katakam",
+            ],
+            "examples": [
+                "Show some verses from Katakam",
+            ],
+            "llm_hints": [],
+        },        
     ]
 
     def get_scripture_by_collection(self, collection_name: str):

copy_chromadb.py

@@ -48,6 +48,11 @@ db_config = {
         "source_collection_name": "taitriya_brahmanam",
         "destination_collection_name": "taitriya_brahmanam",
     },
+    "katakam": {
+        "source_db_path": "../taitriya_brahmanam_ai/chromadb_store",
+        "source_collection_name": "katakam",
+        "destination_collection_name": "katakam",
+    },
 }
 
 parser = argparse.ArgumentParser(description="My app with database parameter")