I understand that Ollama can be used as an LLM provider via the OpenAI compatible API, but how to utilize it as an embeddings provider. According to the blog, Ollama’s OpenAI API compatibility for embeddings is still in the works, and since huggingface_hub has an open issue right now where it cannot be used with langchain right now, is there any other way to make the opensource models accessible?
Related Topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Local LLM and Embedding Configuration Issues in Rasa Pro | 9 | 58 | September 12, 2024 | |
| Cannot change from openai to huggingface_hub | 1 | 39 | July 30, 2024 | |
| Hugging Face LLM ‘huggingface_hub.inference_api’ is deprecated, | 4 | 358 | May 6, 2024 | |
| How to use Ollama models in Rasa CALM? | 5 | 485 | May 14, 2024 | |
| Huggingface model | 0 | 91 | May 30, 2024 |