mirror of
https://github.com/khoj-ai/khoj.git
synced 2024-11-27 17:35:07 +01:00
77fa8718d9
Still need quite a bit of clean-up, but this adds a working docker-compose + Dockerfile setup
44 lines
No EOL
1.3 KiB
YAML
44 lines
No EOL
1.3 KiB
YAML
content-type:
|
|
org:
|
|
input-files: null
|
|
input-filter: "/data/notes/*.org"
|
|
compressed-jsonl: "/data/generated/.notes.json.gz"
|
|
embeddings-file: "/data/generated/.note_embeddings.pt"
|
|
|
|
ledger:
|
|
# input-files: null
|
|
# input-filter: /data/ledger/*.beancount
|
|
# compressed-jsonl: /data/generated/.transactions.jsonl.gz
|
|
# embeddings-file: /data/generated/.transaction_embeddings.pt
|
|
|
|
image:
|
|
# input-directory: "/data/images/"
|
|
# embeddings-file: "/data/generated/.image_embeddings.pt"
|
|
# batch-size: 50
|
|
# use-xmp-metadata: "no"
|
|
|
|
music:
|
|
# input-files: null
|
|
# input-filter: "/data/music/*.org"
|
|
# compressed-jsonl: "/data/generated/.songs.jsonl.gz"
|
|
# embeddings-file: "/data/generated/.song_embeddings.pt"
|
|
|
|
search-type:
|
|
symmetric:
|
|
encoder: "sentence-transformers/paraphrase-MiniLM-L6-v2"
|
|
cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
|
|
model_directory: "/data/models/.symmetric"
|
|
|
|
asymmetric:
|
|
encoder: "sentence-transformers/msmarco-MiniLM-L-6-v3"
|
|
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/conversation/.conversation_logs.json" |