|
log_dir: 'storage/logs' |
|
log_chunk_dir: 'storage/logs/chunks' |
|
device: 'cpu' |
|
|
|
vectorstore: |
|
load_from_HF: True |
|
reparse_files: True |
|
data_path: 'storage/data' |
|
url_file_path: 'storage/data/urls.txt' |
|
expand_urls: True |
|
db_option : 'RAGatouille' |
|
db_path : 'vectorstores' |
|
model : 'sentence-transformers/all-MiniLM-L6-v2' |
|
search_top_k : 3 |
|
score_threshold : 0.2 |
|
|
|
faiss_params: |
|
index_path: 'vectorstores/faiss.index' |
|
index_type: 'Flat' |
|
index_dimension: 384 |
|
index_nlist: 100 |
|
index_nprobe: 10 |
|
|
|
colbert_params: |
|
index_name: "new_idx" |
|
|
|
llm_params: |
|
llm_arch: 'langchain' |
|
use_history: True |
|
generate_follow_up: False |
|
memory_window: 3 |
|
llm_style: 'Normal' |
|
llm_loader: 'gpt-4o-mini' |
|
openai_params: |
|
temperature: 0.7 |
|
local_llm_params: |
|
temperature: 0.7 |
|
repo_id: 'TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF' |
|
filename: 'tinyllama-1.1b-chat-v1.0.Q5_0.gguf' |
|
model_path: 'storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf' |
|
stream: False |
|
pdf_reader: 'gpt' |
|
|
|
chat_logging: |
|
log_chat: True |
|
platform: 'literalai' |
|
callbacks: True |
|
|
|
splitter_options: |
|
use_splitter: True |
|
split_by_token : True |
|
remove_leftover_delimiters: True |
|
remove_chunks: False |
|
chunking_mode: 'semantic' |
|
chunk_size : 300 |
|
chunk_overlap : 30 |
|
chunk_separators : ["\n\n", "\n", " ", ""] |
|
front_chunks_to_remove : null |
|
last_chunks_to_remove : null |
|
delimiters_to_remove : ['\t', '\n', ' ', ' '] |
|
|