klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-06 13:22:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge sample_config, docker_sample_config yml into a single sample_config.yml

Browse Source 
- Update readme to indicate how to update the new sample_config to run on test data
This commit is contained in:
Debanjum Singh Solanky
2022-01-29 01:32:12 -05:00
parent 2bc2780501
commit 3e889760c7
4 changed files with 31 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
sample_config.yml
View File

@@ -1,44 +1,47 @@
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: ["tests/data/main_readme.org", "tests/data/interface_emacs_readme.org"]
input-filter: null
compressed-jsonl: "tests/data/.notes.json.gz"
embeddings-file: "tests/data/.note_embeddings.pt"
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: tests/data/*.beancount
compressed-jsonl: tests/data/.transactions.jsonl.gz
embeddings-file: tests/data/.transaction_embeddings.pt
input-filter: /data/ledger/*.beancount
compressed-jsonl: /data/generated/transactions.jsonl.gz
embeddings-file: /data/generated/transaction_embeddings.pt
image:
input-directory: "tests/data"
embeddings-file: "tests/data/.image_embeddings.pt"
input-directory: "/data/images/"
embeddings-file: "/data/generated/image_embeddings.pt"
batch-size: 50
use-xmp-metadata: false
use-xmp-metadata: true
music:
input-files: ["tests/data/music.org"]
input-files: ["/data/music/music.org"]
input-filter: null
compressed-jsonl: "tests/data/.songs.jsonl.gz"
embeddings-file: "tests/data/.song_embeddings.pt"
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: "tests/data/.symmetric"
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: "tests/data/.asymmetric"
model_directory: "/data/models/asymmetric"
image:
encoder: "clip-ViT-B-32"
model_directory: "tests/data/.image_encoder"
model_directory: "/data/models/image_encoder"
processor:
conversation:
openai-api-key: null
conversation-logfile: "tests/data/.conversation_logs.json"
conversation-logfile: "/data/generated/conversation_logs.json"