Skip to main content
Use this setup when you want semantic search without an external embedding API. It is useful on small CPU-only VPS instances where Ollama can be slower than the default vector indexing settings. KiwiFS supports two tuning knobs for this case:
  • [search.vector].worker_count lowers concurrent embed and upsert workers.
  • [search.vector.embedder].timeout raises the Ollama HTTP request timeout.
The defaults stay optimized for normal machines: worker_count defaults to 5, and the Ollama timeout defaults to 30s.

​
Prerequisites

  • KiwiFS with the vector tuning options from kiwifs/kiwifs#20.
  • An Ollama server reachable from the KiwiFS process.
  • An embedding model pulled into Ollama.
ollama pull nomic-embed-text

​
Configure KiwiFS

Create or update .kiwi/config.toml in your knowledge root. 
[search]
engine = "sqlite"

[search.vector]
enabled = true
worker_count = 1

[search.vector.embedder]
provider = "ollama"
base_url = "http://127.0.0.1:11434"
model = "nomic-embed-text"
timeout = "120s"

[search.vector.store]
provider = "sqlite-vec"
This keeps the full stack local:
  • Ollama generates embeddings on the same machine.
  • sqlite-vec stores vectors inside the KiwiFS search database.
  • No embedding API key is required.
Use Go duration strings for timeout, such as 60s, 120s, or 3m.

​
Choose the Ollama URL

The correct base_url depends on where KiwiFS runs.
Use the local Ollama URL.
[search.vector.embedder]
provider = "ollama"
base_url = "http://127.0.0.1:11434"
model = "nomic-embed-text"
timeout = "120s"
On Linux, add a host gateway entry to the KiwiFS container and use host.docker.internal.
services:
  kiwifs:
    image: ameliaanhlam/kiwifs:latest
    extra_hosts:
      - "host.docker.internal:host-gateway"
Then configure KiwiFS:
[search.vector.embedder]
provider = "ollama"
base_url = "http://host.docker.internal:11434"
model = "nomic-embed-text"
timeout = "120s"
Use the Ollama service name as the hostname.
[search.vector.embedder]
provider = "ollama"
base_url = "http://ollama:11434"
model = "nomic-embed-text"
timeout = "120s"

​
Index existing files

After enabling vector search, rebuild the search indexes once. 
kiwifs reindex --root ./knowledge
For a large vault on a small VPS, keep worker_count = 1 for the first reindex. Raise it later only if CPU, memory, and Ollama latency remain stable.

​
When to tune the values

SymptomChange
Ollama requests time out during reindexingIncrease timeout, for example from 120s to 3m
CPU stays saturated or the VPS becomes unresponsiveLower worker_count to 1
Reindexing is stable but too slowTry worker_count = 2
Vector search works, but new writes appear in semantic search slowlyKeep worker_count low and run kiwifs reindex during low-traffic periods

​
Troubleshooting

​
Check Ollama from the KiwiFS machine

curl http://127.0.0.1:11434/api/tags
If KiwiFS runs in Docker, run the check from inside the container and use the same hostname as base_url. 
curl http://host.docker.internal:11434/api/tags

​
Confirm the model exists

ollama list
If nomic-embed-text is missing, pull it: 
ollama pull nomic-embed-text

​
Recover from a failed first reindex

Keep the same config, raise timeout, and run reindex again. The vector index is derivative data, so KiwiFS can rebuild it from the markdown files. 
kiwifs reindex --root ./knowledge
Last modified on May 22, 2026