khoj/config/khoj_sample.yml
Debanjum Singh Solanky b3ebb01beb Disable image search for now as unable to load CLIP model
Loading CLIP Model from Sentence-Transformer is failing
See https://github.com/UKPLab/sentence-transformers/issues/1659 for details
2022-08-04 02:20:45 +03:00

53 lines
No EOL
1.7 KiB
YAML

content-type:
# The /data/folder/ prefix to the folders is here because this is
# the directory to which the local files are copied in the docker-compose.
# If changing, the docker-compose volumes should also be changed to match.
org:
input-files: null
input-filter: "/data/notes/*.org"
compressed-jsonl: "/data/embeddings/notes.jsonl.gz"
embeddings-file: "/data/embeddings/note_embeddings.pt"
markdown:
input-files: null
input-filter: "/data/markdown/*.md"
compressed-jsonl: "/data/embeddings/markdown.jsonl.gz"
embeddings-file: "/data/embeddings/markdown_embeddings.pt"
ledger:
input-files: null
input-filter: /data/ledger/*.beancount
compressed-jsonl: /data/embeddings/transactions.jsonl.gz
embeddings-file: /data/embeddings/transaction_embeddings.pt
# image:
# input-directories: ["/data/images/"]
# embeddings-file: "/data/embeddings/image_embeddings.pt"
# batch-size: 50
# use-xmp-metadata: true
music:
input-files: ["/data/music/music.org"]
input-filter: null
compressed-jsonl: "/data/embeddings/songs.jsonl.gz"
embeddings-file: "/data/embeddings/song_embeddings.pt"
search-type:
symmetric:
encoder: "sentence-transformers/all-MiniLM-L6-v2"
cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
model_directory: "/data/models/symmetric"
asymmetric:
encoder: "sentence-transformers/multi-qa-MiniLM-L6-cos-v1"
cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
model_directory: "/data/models/asymmetric"
image:
encoder: "clip-ViT-B-32"
model_directory: "/data/models/image_encoder"
processor:
conversation:
openai-api-key: null
conversation-logfile: "/data/embeddings/conversation_logs.json"