mirror of
https://github.com/amithkoujalgi/ollama4j.git
synced 2025-11-02 09:30:41 +01:00
0aeabcc963
Refactored error handling in OllamaChatEndpointCaller by extracting status code checks into a helper method. Improved logging for image loading errors in OllamaChatRequestBuilder. Updated integration and unit tests to relax assertions and clarify comments. Minor documentation formatting fixes and Makefile improvement for reproducible npm installs.
1.4 KiB
1.4 KiB
sidebar_position
| sidebar_position |
|---|
| 1 |
import CodeEmbed from '@site/src/components/CodeEmbed';
Generate Embeddings
Generate embeddings from a model.
Using embed()
:::tip[LLM Response]
[
[
0.010000081,
-0.0017487297,
0.050126992,
0.04694895,
0.055186987,
0.008570699,
0.10545243,
-0.02591801,
0.1296789,
],
[
-0.009868476,
0.060335685,
0.025288988,
-0.0062160683,
0.07281043,
0.017217565,
0.090314455,
-0.051715206,
]
]
:::
You could also use the OllamaEmbedRequestModel to specify the options such as seed, temperature, etc., to apply
for generating embeddings.
You will get a response similar to:
:::tip[LLM Response]
[
[
0.010000081,
-0.0017487297,
0.050126992,
0.04694895,
0.055186987,
0.008570699,
0.10545243,
-0.02591801,
0.1296789,
],
[
-0.009868476,
0.060335685,
0.025288988,
-0.0062160683,
0.07281043,
0.017217565,
0.090314455,
-0.051715206,
]
]
:::