apps/ai_tutor/config/config.yml

log_dir: "storage/logs" # str
log_chunk_dir: "storage/logs/chunks" # str
device: "cpu" # str [cuda, cpu]

vectorstore:
  load_from_HF: false # bool
  reparse_files: true # bool
  data_path: "storage/data" # str
  url_file_path: "storage/data/urls.txt" # str
  expand_urls: false # bool
  db_option: "FAISS" # str [FAISS, Chroma, RAGatouille, RAPTOR]
  db_path: "vectorstores" # str
  model: "text-embedding-ada-002" # str [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002']
  search_top_k: 5 # int
  score_threshold: 0.3 # float

  faiss_params: # Not used as of now
    index_path: "vectorstores/faiss.index" # str
    index_type: "Flat" # str [Flat, HNSW, IVF]
    index_dimension: 384 # int
    index_nlist: 100 # int
    index_nprobe: 10 # int

  colbert_params:
    index_name: "new_idx" # str

llm_params:
  llm_arch: "langchain" # [langchain]
  use_history: true # bool
  generate_follow_up: false # bool
  memory_window: 3 # int
  llm_style: "Normal" # str [Normal, ELI5]
  llm_loader: "gpt-4o-mini" # str [local_llm, gpt-3.5-turbo-1106, gpt-4, gpt-4o-mini]
  openai_params:
    temperature: 0.7 # float
  local_llm_params:
    temperature: 0.7 # float
    repo_id: "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF" # HuggingFace repo id
    filename: "tinyllama-1.1b-chat-v1.0.Q5_0.gguf" # Specific name of gguf file in the repo
    model_path: "storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf" # Path to the model file
  stream: false # bool
  pdf_reader: "gpt" # str [llama, pymupdf, gpt]

chat_logging:
  log_chat: true # bool
  platform: "literalai"
  callbacks: true # bool

splitter_options:
  use_splitter: true # bool
  split_by_token: true # bool
  remove_leftover_delimiters: true # bool
  remove_chunks: false # bool
  chunking_mode: "semantic" # str [fixed, semantic]
  chunk_size: 300 # int
  chunk_overlap: 30 # int
  chunk_separators: ["\n\n", "\n", " ", ""] # list of strings
  front_chunks_to_remove:      # int or None
  last_chunks_to_remove:      # int or None
  delimiters_to_remove: ['\t', '\n', "   ", "  "] # list of strings