Commit graph

7 commits

Author SHA1 Message Date
turboderp
122d87ac36 Tree: Format 2025-06-15 19:33:14 +02:00
turboderp
21c5af48e1 Tree: Format 2025-06-15 19:30:38 +02:00
turboderp
1c9891bf04 Exl3: Add vision capability 2025-06-15 19:22:51 +02:00
kingbri
54fda0dc09 Tree: Format
Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
2025-02-07 18:03:33 -05:00
kingbri
96e8375ec8 Multimodal: Fix memory leak with MMEmbeddings
On a basic python class, class attributes are handled by reference,
meaning that every instance of embeddings would attach to that reference
and allocate more memory.

Switch to a Pydantic class and factory methods when instantiating.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
2025-02-02 12:21:19 -05:00
kingbri
c652a6e030 API: Transform multimodal into an actual class
Migrate the add method into the class itself. Also, a BaseModel isn't
needed here since this isn't a serialized class.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-11-20 00:06:20 -05:00
DocShotgun
dd41eec8a4 OAI: Initial vision support in OAI chat completions
* Support image_url inputs containing URLs or base64 strings following OAI vision spec
* Use async lru cache for image embeddings
* Add generic wrapper class for multimodal embeddings
2024-11-17 21:23:09 -08:00