From 11a18cc45234a4af770682e78bec76b3ef5bf53a Mon Sep 17 00:00:00 2001 From: Debanjum Singh Solanky Date: Mon, 6 Feb 2023 20:57:06 -0300 Subject: [PATCH] Update khoj docker config to index sub directories for text content - Khoj supports indexing subdirectories but the khoj docker config wasn't updated to support the same - This should also allow khoj docker users to index multiple separate directory trees by mounting them into separate sub folders within /data//. For e.g /data/org/dir1, /data/org/dir2 etc in khoj_docker.yml --- config/khoj_docker.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/config/khoj_docker.yml b/config/khoj_docker.yml index 176a7b1e..cf3535ea 100644 --- a/config/khoj_docker.yml +++ b/config/khoj_docker.yml @@ -4,20 +4,20 @@ content-type: # If changing, the docker-compose volumes should also be changed to match. org: input-files: null - input-filter: ["/data/org/*.org"] + input-filter: ["/data/org/**/*.org"] compressed-jsonl: "/data/embeddings/notes.jsonl.gz" embeddings-file: "/data/embeddings/note_embeddings.pt" index_heading_entries: false markdown: input-files: null - input-filter: ["/data/markdown/*.md"] + 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"] + input-filter: ["/data/ledger/**/*.beancount"] compressed-jsonl: /data/embeddings/transactions.jsonl.gz embeddings-file: /data/embeddings/transaction_embeddings.pt