Ettore Di Giacinto d5da8c3509

feat(templates): extract text from multimodal requests (#3866) ...

When offloading template construction to the backend, we want to keep
text around in case of multimodal requests.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

2024-10-17 17:33:50 +02:00

..

backend_suite_test.go

feat: extract output with regexes from LLMs (#3491)

2024-09-13 13:27:36 +02:00

embeddings.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

image.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

llm_test.go

feat: extract output with regexes from LLMs (#3491)

2024-09-13 13:27:36 +02:00

llm.go

feat(templates): extract text from multimodal requests (#3866)

2024-10-17 17:33:50 +02:00

options.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

rerank.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

soundgeneration.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

stores.go

chore: fix go.mod module (#2635)

2024-06-23 08:24:36 +00:00

token_metrics.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

tokenize.go

chore: simplify model loading (#3715)

2024-10-02 08:59:06 +02:00

transcript.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00

tts.go

feat: track internally started models by ID (#3693)

2024-10-02 08:55:58 +02:00