klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-09 05:39:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Create khoj_sample file with all configurable fields in one place

Browse Source 
- Reason
  - Simplifies code. No merge_dict required
  - 1 place for user to see all configurables, defaults and required values

- Details
  - Remove default_config from code. Set defaults in khoj_sample.yml itself
  - Keep fields required to be set by user as empty in khoj_sample to YAML
  - Set defaults for fields not requiring configuration by user
This commit is contained in:
Debanjum Singh Solanky
2022-08-04 22:57:35 +03:00
parent 4788143aa6
commit f78d6ae754
2 changed files with 38 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
config/khoj_sample.yml
View File

@@ -1,53 +1,51 @@
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"
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: null
input-filter: "/data/markdown/*.md"
compressed-jsonl: "/data/embeddings/markdown.jsonl.gz"
embeddings-file: "/data/embeddings/markdown_embeddings.pt"
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: null
input-filter: /data/ledger/*.beancount
compressed-jsonl: /data/embeddings/transactions.jsonl.gz
embeddings-file: /data/embeddings/transaction_embeddings.pt
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: ["/data/images/"]
# embeddings-file: "/data/embeddings/image_embeddings.pt"
# batch-size: 50
# use-xmp-metadata: true
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: 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"
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: "/data/models/symmetric"
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: "/data/models/asymmetric"
model_directory: "~/.khoj/search/asymmetric/"
image:
encoder: "clip-ViT-B-32"
model_directory: "/data/models/image_encoder"
encoder: "sentence-transformers/clip-ViT-B-32"
model_directory: "~/.khoj/search/image/"
processor:
conversation:
openai-api-key: null
conversation-logfile: "/data/embeddings/conversation_logs.json"
openai-api-key: # "YOUR_OPENAI_API_KEY"
conversation-logfile: "~/.khoj/processor/conversation/conversation_logs.json"