Ollama v0.3.4 — Release Notes & Engineering Impact

<img width="1548" alt="Screenshot 2024-08-06 at 8 16 44 PM" src="https://github.com/user-attachments/assets/9a53a40e-4649-4d67-8433-052a5941a5b6"> ## New embedding models * [BGE-M3](https://ollama.com/library/bge-m3): a large embedding model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity. * [BGE-Large](https://ollama.com/library/bge-large): a large embedding model trained in english. * [Paraphrase-Multilingual](https://ollama.com/library/paraphrase-multilingual): A multilingual embedding model trained on parallel data for 50+ languages. ## New embedding API with batch support Ollama now supports a new API endpoint `/api/embed` for embedding generation: ``` curl http://localhost:11434/api/embed -d '{ "model": "all-minilm", "input": ["Why is the sky blue?", "Why is the grass green?"] }' ``` This API endpoint supports new features: * **Batches**: generate embeddings for several documents in one request * **Normalized embeddings**: embeddings are now normalized, improving similarity results * **Truncation**: a new `truncate` parameter that will error if set to `false` * **Metrics**: responses include `load_duration`, `total_duration` and `prompt_eval_count` metrics See the [API documentation](https://github.com/ollama/ollama/blob/main/docs/api.md#generate-embeddings) for more details and examples. ## What's Changed * Fixed initial slow download speeds on Windows * NUMA support will now be autodetected by Ollama to improve performance * Fixed issue where the `/api/embed` would sometimes return embedding results out of order ## New Contributors * @av made their first contribution in https://github.com/ollama/ollama/pull/6147 * @sryu1 made their first contribution in https://github.com/ollama/ollama/pull/6151 * @rick-github made their first contribution in https://github.com/ollama/ollama/pull/6154 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.3.3...v0.3.4