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.
+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 and uses the [OpenAI API](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings). This is implemented by several project besides OpenAI itself, including the python-based fastembed-server found in `supplemental/search/fastembed-api`.
-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.
+The default settings will support a setup where both the fastembed server and Qdrant run on the same system as pleroma.
## Meilisearch
Note that it's quite a bit more memory hungry than PostgreSQL (around 4-5G for ~1.2 million
posts while idle and up to 7G while indexing initially). The disk usage for this additional index is also
around 4 gigabytes. Like [RUM](./cheatsheet.md#rum-indexing-for-full-text-search) indexes, it offers considerably
higher performance and ordering by timestamp in a reasonable amount of time.
Additionally, the search results seem to be more accurate.
Due to high memory usage, it may be best to set it up on a different machine, if running pleroma on a low-resource
computer, and use private key authentication to secure the remote search instance.
To use [meilisearch](https://www.meilisearch.com/), set the search module to `Pleroma.Search.Meilisearch`: