Initial commit

2025-03-14 17:33:18 +09:00
parent ba9c1a4a5f
commit 6814230bfb
61 changed files with 2087124 additions and 4 deletions
--- a/projects/example_01/config/chunk.yaml
+++ b/projects/example_01/config/chunk.yaml
@@ -0,0 +1,13 @@
+modules:
+  - module_type: llama_index_chunk
+    chunk_method: Token
+    chunk_size: [200, 800]
+    chunk_overlap: [30, 200]
+    add_file_name: ko 
+  - module_type: llama_index_chunk
+    chunk_method: Semantic_llama_index
+    embed_model: hf_snowflake-arctic-embed-l-v2.0-ko
+    add_file_name: ko 
+  - module_type: langchain_chunk
+    chunk_method: recursivecharacter
+    separators: [ " ", "\n" ]
--- a/projects/example_01/config/parse.yaml
+++ b/projects/example_01/config/parse.yaml
@@ -0,0 +1,4 @@
+modules:
+  - module_type: langchain_parse
+    file_type: pdf
+    parse_method: [ pdfminer, pdfplumber, pypdfium2, pypdf, pymupdf ]