Adding ClipVitB32 model so text-to-image search is supported. #126
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
Author
|
Done. Thanks for looking at this very quickly. |
github-actions bot
pushed a commit
that referenced
this pull request
Nov 23, 2024
# [4.2.0](v4.1.2...v4.2.0) (2024-11-23) ### Features * Added ClipVitB32 model to support text-to-image search. ([#126](#126)) ([a890a61](a890a61)) ## [4.2.0](v4.1.2...v4.2.0) (2024-11-23) ### 🍕 Features * Added ClipVitB32 model to support text-to-image search. ([#126](#126)) ([a890a61](a890a61)) ### 🔁 Continuous Integration * Use ONNX version as cache key for the ONNX cache ([#127](#127)) ([f19a540](f19a540))
|
🎉 This PR is included in version 4.2.0 🎉 The release is available on:
Your semantic-release bot 📦🚀 |
Contributor
Author
|
Thank you! |
greenhat616
added a commit
to gety-ai/fastembed-rs
that referenced
this pull request
Dec 2, 2024
* chore: bump ort recv * docs: Support notice in README.md (Anush008#123) Signed-off-by: Anush008 <[email protected]> * chore: Bump ort to 2.0.0.-rc8 with "ort/half" enabled (Anush008#124) * chore(release): 4.1.1 [skip ci] ## [4.1.1](Anush008/fastembed-rs@v4.1.0...v4.1.1) (2024-11-21) ## [4.1.1](Anush008/fastembed-rs@v4.1.0...v4.1.1) (2024-11-21) ### 📝 Documentation * Support notice in README.md ([Anush008#123](Anush008#123)) ([a3794de](Anush008@a3794de)) ### 🧹 Chores * Bump ort to 2.0.0.-rc8 with "ort/half" enabled ([Anush008#124](Anush008#124)) ([f4844a8](Anush008@f4844a8)) * chore: Bump ort to v2.0.0-rc.9 (Anush008#125) * chore: Bump ort to v2.0.0-rc.9 Signed-off-by: Anush008 <[email protected]> * refactor: Dedup imports Signed-off-by: Anush008 <[email protected]> * ci: Custom link v1.20.1 ONNX build Signed-off-by: Anush008 <[email protected]> * chore: no 'half' --------- Signed-off-by: Anush008 <[email protected]> * chore(release): 4.1.2 [skip ci] ## [4.1.2](Anush008/fastembed-rs@v4.1.1...v4.1.2) (2024-11-22) ## [4.1.2](Anush008/fastembed-rs@v4.1.1...v4.1.2) (2024-11-22) ### 🧹 Chores * Bump ort to v2.0.0-rc.9 ([Anush008#125](Anush008#125)) ([87f4ced](Anush008@87f4ced)) * ci: Use ONNX version as cache key for the ONNX cache (Anush008#127) Signed-off-by: Anush008 <[email protected]> * feat: Added ClipVitB32 model to support text-to-image search. (Anush008#126) * chore(release): 4.2.0 [skip ci] # [4.2.0](Anush008/fastembed-rs@v4.1.2...v4.2.0) (2024-11-23) ### Features * Added ClipVitB32 model to support text-to-image search. ([Anush008#126](Anush008#126)) ([a890a61](Anush008@a890a61)) ## [4.2.0](Anush008/fastembed-rs@v4.1.2...v4.2.0) (2024-11-23) ### 🍕 Features * Added ClipVitB32 model to support text-to-image search. ([Anush008#126](Anush008#126)) ([a890a61](Anush008@a890a61)) ### 🔁 Continuous Integration * Use ONNX version as cache key for the ONNX cache ([Anush008#127](Anush008#127)) ([f19a540](Anush008@f19a540)) * refactor: Turn most panics into recoverable errors (Anush008#128) * for image embeddings, turn some panics into returned errors * turn more panics into recoverable errors * Simplify collection of image embeddings Co-authored-by: Anush <[email protected]> * Pass errors in sparse text embedding and reranking batches onto the user instead of panicking * fix warnings: only import anyhow::Context if online feature enabled * cargo fmt --------- Co-authored-by: Anush <[email protected]> * chore(release): 4.2.1 [skip ci] ## [4.2.1](Anush008/fastembed-rs@v4.2.0...v4.2.1) (2024-11-26) ## [4.2.1](Anush008/fastembed-rs@v4.2.0...v4.2.1) (2024-11-26) ### 🧑💻 Code Refactoring * Turn most panics into recoverable errors ([Anush008#128](Anush008#128)) ([86594fc](Anush008@86594fc)) * feat: Support for nomic-embed-vision-v1.5 image embeddings model (Anush008#129) * adds support for nomic-embed-vision-v1.5 image embeddings model * ignore optional test * chore(release): 4.3.0 [skip ci] # [4.3.0](Anush008/fastembed-rs@v4.2.1...v4.3.0) (2024-11-27) ### Features * Support for nomic-embed-vision-v1.5 image embeddings model ([Anush008#129](Anush008#129)) ([76751ec](Anush008@76751ec)) ## [4.3.0](Anush008/fastembed-rs@v4.2.1...v4.3.0) (2024-11-27) ### 🍕 Features * Support for nomic-embed-vision-v1.5 image embeddings model ([Anush008#129](Anush008#129)) ([76751ec](Anush008@76751ec)) * chore: bump onnx version to 1.20.1 --------- Signed-off-by: Anush008 <[email protected]> Co-authored-by: Anush008 <[email protected]> Co-authored-by: Daniel Boros <[email protected]> Co-authored-by: Bernard van Gastel <[email protected]> Co-authored-by: llenck <[email protected]> Co-authored-by: Alex Rozgo <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Thanks for this great crate. To support text-to-image search, it is useful to have
ClipVitB32text embedding, as this maps to the same vector space as theClipVitB32image embedder.Let me know if changes are needed to this pull request.