mirror of
https://github.com/khoj-ai/khoj.git
synced 2024-12-02 20:03:01 +01:00
d4072974d7
- CLIP Image score and XMP metadata score are not combining well.
When combined they give non sensical results. Enable only once
figure how best to combine the two.
- Show scores with higher precision for image search
- Image search scores seem to be mostly be between 0.2 - 0.3 for some reason
- Higher precision scores make it easier to understand the quality
of returned results perceived by the model itself
51 lines
2.1 KiB
YAML
51 lines
2.1 KiB
YAML
content-type:
|
|
org:
|
|
input-files: # ["/path/to/org-file.org"] REQUIRED IF input-filter IS NOT SET OR
|
|
input-filter: # /path/to/org/*.org REQUIRED IF input-files IS NOT SET
|
|
compressed-jsonl: "~/.khoj/content/org/org.jsonl.gz"
|
|
embeddings-file: "~/.khoj/content/org/org_embeddings.pt"
|
|
|
|
markdown:
|
|
input-files: # ["/path/to/markdown-file.md"] REQUIRED IF input-filter IS NOT SET OR
|
|
input-filter: # "/path/to/markdown/*.md" REQUIRED IF input-files IS NOT SET
|
|
compressed-jsonl: "~/.khoj/content/markdown/markdown.jsonl.gz"
|
|
embeddings-file: "~/.khoj/content/markdown/markdown_embeddings.pt"
|
|
|
|
ledger:
|
|
input-files: # ["/path/to/ledger-file.beancount"] REQUIRED IF input-filter is not set OR
|
|
input-filter: # /path/to/ledger/*.beancount REQUIRED IF input-files is not set
|
|
compressed-jsonl: "~/.khoj/content/ledger/ledger.jsonl.gz"
|
|
embeddings-file: "~/.khoj/content/ledger/ledger_embeddings.pt"
|
|
|
|
image:
|
|
input-directories: # ["/path/to/images/"] REQUIRED IF input-filter IS NOT SET OR
|
|
input-filter: # /path/to/images/*.jpg REQUIRED IF input-directories IS NOT SET
|
|
embeddings-file: "~/.khoj/content/image/image_embeddings.pt"
|
|
batch-size: 50
|
|
use-xmp-metadata: false
|
|
|
|
music:
|
|
input-files: # ["/path/to/music-file.org"] REQUIRED IF input-filter IS NOT SET OR
|
|
input-filter: # /path/to/music/*.org REQUIRED IF input-files IS NOT SET
|
|
compressed-jsonl: "~/.khoj/content/music/music.jsonl.gz"
|
|
embeddings-file: "~/.khoj/content/music/music_embeddings.pt"
|
|
|
|
search-type:
|
|
symmetric:
|
|
encoder: "sentence-transformers/all-MiniLM-L6-v2"
|
|
cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
|
|
model_directory: "~/.khoj/search/symmetric/"
|
|
|
|
asymmetric:
|
|
encoder: "sentence-transformers/multi-qa-MiniLM-L6-cos-v1"
|
|
cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
|
|
model_directory: "~/.khoj/search/asymmetric/"
|
|
|
|
image:
|
|
encoder: "sentence-transformers/clip-ViT-B-32"
|
|
model_directory: "~/.khoj/search/image/"
|
|
|
|
processor:
|
|
conversation:
|
|
openai-api-key: # "YOUR_OPENAI_API_KEY"
|
|
conversation-logfile: "~/.khoj/processor/conversation/conversation_logs.json"
|