Docs/Search: Add basic documentation of the qdrant search

This commit is contained in:
Lain Soykaf 2024-05-14 16:56:58 +04:00
parent 1490ff30af
commit c50f0f31f4
1 changed files with 6 additions and 0 deletions

View File

@ -10,6 +10,12 @@ To use built-in search that has no external dependencies, set the search module
While it has no external dependencies, it has problems with performance and relevancy. While it has no external dependencies, it has problems with performance and relevancy.
## QdrantSearch
This uses the vector search engine [Qdrant](https://qdrant.tech) to search the posts in a vector space. This needs a way to generate embeddings, for now only the [Ollama](Ollama) api is supported.
The default settings will support a setup where both Ollama and Qdrant run on the same system as pleroma. The embedding model used by Ollama will need to be pulled first (e.g. `ollama pull snowflake-arctic-embed:xs`) for the embedding to work.
## Meilisearch ## Meilisearch
Note that it's quite a bit more memory hungry than PostgreSQL (around 4-5G for ~1.2 million Note that it's quite a bit more memory hungry than PostgreSQL (around 4-5G for ~1.2 million