marqo
marqo copied to clipboard
marqo-ai
Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
* **What kind of change does this PR introduce?** (Bug fix, feature, docs update, ...) * **What is the current behavior?** (You can also link to an open issue here)...
* **What kind of change does this PR introduce?** (Bug fix, feature, docs update, ...) Bug fix * **What is the current behavior?** (You can also link to an open...
**Is your feature request related to a problem? Please describe.** There is no way to have a searching model that is different from the indexing model. There is no way...
https://github.com/baaivision/EVA
**Is your feature request related to a problem? Please describe.** There is no way to update an index's model **Describe the solution you'd like** An advanced feature: update an index's...
**Is your feature request related to a problem? Please describe.** Currently we don’t log the error or stack trace. **Describe the solution you'd like** We can update the internal_exeception_handler in...
**Describe the bug** Internal error occurs on add_docs when split_length < split_overlap. This issue was raised on our forums [here](https://community.marqo.ai/t/error-500-adding-documents/). **Reproducing the issue** _To reproduce:_ ``` # create index: curl...
**Describe the bug** When indexing multimodal data with images into a text model (`hf/all_datasets_v4_MiniLM-L6`) raises a 500 internal error. Marqo output: ```File "/app/src/marqo/tensor_search/tensor_search.py", line 2046, in vectorise_multimodal_combination_field image_vectors = s2_inference.vectorise(...
