Farid Karimli commited on
Commit
0f736a4
·
1 Parent(s): 96bddf1

Config change

Browse files
Files changed (1) hide show
  1. apps/ai_tutor/config/config.yml +5 -5
apps/ai_tutor/config/config.yml CHANGED
@@ -7,7 +7,7 @@ vectorstore:
7
  reparse_files: True # bool
8
  data_path: "storage/data" # str
9
  url_file_path: "storage/data/urls.txt" # str
10
- expand_urls: True # bool
11
  db_option: "FAISS" # str [FAISS, Chroma, RAGatouille, RAPTOR]
12
  db_path: "vectorstores" # str
13
  model: "sentence-transformers/all-MiniLM-L6-v2" # str [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002']
@@ -38,7 +38,7 @@ llm_params:
38
  repo_id: "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF" # HuggingFace repo id
39
  filename: "tinyllama-1.1b-chat-v1.0.Q5_0.gguf" # Specific name of gguf file in the repo
40
  model_path: "storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf" # Path to the model file
41
- stream: False # bool
42
  pdf_reader: "pymupdf" # str [llama, pymupdf, gpt]
43
 
44
  chat_logging:
@@ -51,9 +51,9 @@ splitter_options:
51
  split_by_token: True # bool
52
  remove_leftover_delimiters: True # bool
53
  remove_chunks: False # bool
54
- chunking_mode: "semantic" # str [fixed, semantic]
55
- chunk_size: 1000 # int
56
- chunk_overlap: 100 # int
57
  chunk_separators: ["\n\n", "\n", " ", ""] # list of strings
58
  front_chunks_to_remove: null # int or None
59
  last_chunks_to_remove: null # int or None
 
7
  reparse_files: True # bool
8
  data_path: "storage/data" # str
9
  url_file_path: "storage/data/urls.txt" # str
10
+ expand_urls: False # bool
11
  db_option: "FAISS" # str [FAISS, Chroma, RAGatouille, RAPTOR]
12
  db_path: "vectorstores" # str
13
  model: "sentence-transformers/all-MiniLM-L6-v2" # str [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002']
 
38
  repo_id: "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF" # HuggingFace repo id
39
  filename: "tinyllama-1.1b-chat-v1.0.Q5_0.gguf" # Specific name of gguf file in the repo
40
  model_path: "storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf" # Path to the model file
41
+ stream: True # bool
42
  pdf_reader: "pymupdf" # str [llama, pymupdf, gpt]
43
 
44
  chat_logging:
 
51
  split_by_token: True # bool
52
  remove_leftover_delimiters: True # bool
53
  remove_chunks: False # bool
54
+ chunking_mode: "fixed" # str [fixed, semantic]
55
+ chunk_size: 500 # int
56
+ chunk_overlap: 50 # int
57
  chunk_separators: ["\n\n", "\n", " ", ""] # list of strings
58
  front_chunks_to_remove: null # int or None
59
  last_chunks_to_remove: null # int or None