Nebius SDK and API
Itâd be good to have a full-featured Python SDK and API in addition to the CLI tool. The main reason is that itâd make integration of Nebius AI (following infra-as-code principles) with other tools easier. Some examples from similar platfroms: Runpod SDK https://github.com/runpod/runpod-python Lambda Labs API https://cloud.lambdalabs.com/api/v1/docs
Alex Kim About 2 months ago
đī¸ Nebius AI Studio
Nebius SDK and API
Itâd be good to have a full-featured Python SDK and API in addition to the CLI tool. The main reason is that itâd make integration of Nebius AI (following infra-as-code principles) with other tools easier. Some examples from similar platfroms: Runpod SDK https://github.com/runpod/runpod-python Lambda Labs API https://cloud.lambdalabs.com/api/v1/docs
Alex Kim About 2 months ago
đī¸ Nebius AI Studio
Python inference client
Good for integrations with other libraries like langchain and llamaindex and for increased user visibility. May be useful for in-house LLM, fine-tuning and batch jobs, also to decouple from OpenAI client.
Cyril Kondratenko 2 months ago
đī¸ Nebius AI Studio
Python inference client
Good for integrations with other libraries like langchain and llamaindex and for increased user visibility. May be useful for in-house LLM, fine-tuning and batch jobs, also to decouple from OpenAI client.
Cyril Kondratenko 2 months ago
đī¸ Nebius AI Studio
Function call support
Try inference engine with function call support + provide working example and list limitations (i.e. some inference libraries do not allow âautoâ tool_choice, for example)
Cyril Kondratenko 2 months ago
đī¸ Nebius AI Studio
Function call support
Try inference engine with function call support + provide working example and list limitations (i.e. some inference libraries do not allow âautoâ tool_choice, for example)
Cyril Kondratenko 2 months ago
đī¸ Nebius AI Studio
DeepSeek-Coder-V2-Lite-Instruct
https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct requested by a potential private beta user
Fedor Zhdanov 2 months ago
Other
đī¸ Nebius AI Studio
DeepSeek-Coder-V2-Lite-Instruct
https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct requested by a potential private beta user
Fedor Zhdanov 2 months ago
Other
đī¸ Nebius AI Studio
Embedding models
We are doing a lot of RAG usecases, I wonder if it would be possible to serve Embedding models for text vectorizing
Roman Gaev 3 months ago
đī¸ Nebius AI Studio
Embedding models
We are doing a lot of RAG usecases, I wonder if it would be possible to serve Embedding models for text vectorizing
Roman Gaev 3 months ago
đī¸ Nebius AI Studio
Spark
Currently, we use Spark on our VMs to prepare our training datasets from raw common crawl, but we want not to spend time on supporting it. Can you do Managed Spark in your cloud?
Stepan 4 months ago
Other
đĄ Feature request
Spark
Currently, we use Spark on our VMs to prepare our training datasets from raw common crawl, but we want not to spend time on supporting it. Can you do Managed Spark in your cloud?
Stepan 4 months ago
Other
đĄ Feature request
Vector database
I propose adding a managed vector database service, such as Milvus or Qdrant. This addition would allow us to seamlessly integrate and use your platform within our product without relying on infrastructure from other cloud providers
Simon 4 months ago
Managed Database
đĄ Feature request
Vector database
I propose adding a managed vector database service, such as Milvus or Qdrant. This addition would allow us to seamlessly integrate and use your platform within our product without relying on infrastructure from other cloud providers
Simon 4 months ago
Managed Database
đĄ Feature request
Commoncrawl mirror
As part of our data processing pipeline, we extensively use Common Crawl data. It would be highly beneficial to have an option to download this data directly from your cloud platform. This feature would help us avoid the costs associated with external traffic billing
An Anonymous User 4 months ago
đĄ Feature request
Commoncrawl mirror
As part of our data processing pipeline, we extensively use Common Crawl data. It would be highly beneficial to have an option to download this data directly from your cloud platform. This feature would help us avoid the costs associated with external traffic billing
An Anonymous User 4 months ago
đĄ Feature request
Completed
Solution library
It would be really helpful to have a solution library that offers end-to-end production solutions we can manage ourselves and install using Terraform. Right now, there's no easy way to get started with your products.
An Anonymous User 4 months ago
Other
đĄ Feature request
Completed
Solution library
It would be really helpful to have a solution library that offers end-to-end production solutions we can manage ourselves and install using Terraform. Right now, there's no easy way to get started with your products.
An Anonymous User 4 months ago
Other
đĄ Feature request
Managed Spark
We are interested in starting to use Managed Spark in your cloud. Currently, we use Spark on our VMs to prepare our training datasets from raw Common Crawl, but we would prefer not to spend time on supporting it
Nick 4 months ago
Other
đĄ Feature request
Managed Spark
We are interested in starting to use Managed Spark in your cloud. Currently, we use Spark on our VMs to prepare our training datasets from raw Common Crawl, but we would prefer not to spend time on supporting it
Nick 4 months ago
Other
đĄ Feature request