Models - cognis

Model examples enact what happens at the LLM-client layer. Sources under examples/models/.

Name	Scenario	Source
`models_streaming_chat`	Stream a one-line explanation to a CLI chat UI — print tokens as they arrive.	src
`models_embedding`	Find the most similar product description for a search query, using cosine similarity.	src
`models_routing`	Route by intent — short greetings to a fast model, long technical questions to a bigger one.	src
`models_content_blocks`	Caption an image — multimodal `ContentPart::Image`. (Needs a vision model: `COGNIS_OLLAMA_MODEL=llava` or hosted equivalent.)	src

How to run

COGNIS_PROVIDER=ollama COGNIS_OLLAMA_MODEL=llama3.1 \
  cargo run -p cognis-examples --example models_streaming_chat

# For multimodal:
ollama pull llava
COGNIS_PROVIDER=ollama COGNIS_OLLAMA_MODEL=llava \
  cargo run -p cognis-examples --example models_content_blocks

See also

Models and providers

Client::from_env, provider builders, the env-var table.

Streaming

Tokens vs structured events.

Embeddings & stores

Where the embedders feed.