multisourceMultiModalChat/config.yaml at main · prekshivyas/multisourceMultiModalChat · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
ctransformers:
  model_path:
    small: "./models/mistral-7b-instruct-v0.2.Q3_K_S.gguf"
    large:  "./models/mistral-7b-instruct-v0.2.Q5_K_M.gguf"

  model_type: "mistral"
  model_config:
    'max_new_tokens': 256
    'temperature' : 0.2
    'context_length': 2048
    'gpu_layers' : 0 # 32 to put all mistral layers on GPU, might differ for other models
    'threads' : -1

chat_config:
  chat_memory_length: 2
  number_of_retrieved_documents: 3

pdf_text_splitter:
  chunk_size: 1024 # number of characters 1024 roughly equels 256 tokens
  overlap: 50
  separators: ["\n", "\n\n"]

llava_model:
  llava_model_path: "./models/llava/llava_ggml-model-q5_k.gguf"
  clip_model_path: "./models/llava/mmproj-model-f16.gguf"

whisper_model: "openai/whisper-small"

embeddings_path: "BAAI/bge-large-en-v1.5"

chromadb:
  chromadb_path: "chroma_db"
  collection_name: "pdfs"

chat_sessions_database_path: "./chat_sessions/chat_sessions.db"


youtube_api_key: ""

langsmith_api_key: "lsv2_****