Add Nomic embeddings (#594)

* Add Nomic embeddings * Apply suggestions from code review Co-authored-by: Mike Jang <michael.jang@qdrant.io> Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com> * Fix link * Fix link --------- Co-authored-by: Mike Jang <michael.jang@qdrant.io> Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2026-09-28 15:38:33 +02:00 · 2024-02-12 09:46:50 +01:00
parent 1a7d485732
commit 3d78043b01
2 changed files with 52 additions and 0 deletions
@@ -0,0 +1,52 @@
+---
+title: "Nomic"
+weight: 1100
+---
+
+# Nomic
+
+The `nomic-embed-text-v1` model is an open source [8192 context length](https://github.com/nomic-ai/contrastors) text encoder.
+While you can find it on the [Hugging Face Hub](https://huggingface.co/nomic-ai/nomic-embed-text-v1), 
+you may have more success through the [Nomic Text Embeddings](https://docs.nomic.ai/reference/endpoints/nomic-embed-text).
+Once installed, you can configure it with the official Python client or through direct HTTP requests.
+
+You can use Nomic embeddings directly in Qdrant client calls. There is a difference in the way the embeddings
+are obtained for documents and queries. The `task_type` parameter defines the embeddings that you get.
+For documents, set the `task_type` to `search_document`:
+
+```python
+from qdrant_client import QdrantClient, models
+from nomic import embed
+
+output = embed.text(
+    texts=["Qdrant is the best vector database!"],
+    model="nomic-embed-text-v1",
+    task_type="search_document",
+)
+
+qdrant_client = QdrantClient()
+qdrant_client.upsert(
+    collection_name="my-collection",
+    points=models.Batch(
+        ids=[1, 2],
+        vectors=output["embeddings"],
+    ),
+)
+```
+
+To query the collection, set the `task_type` to `search_query`:
+
+```python
+output = embed.text(
+    texts=["What is the best vector database?"],
+    model="nomic-embed-text-v1",
+    task_type="search_query",
+)
+
+qdrant_client.search(
+    collection_name="my-collection",
+    query=output["embeddings"][0],
+)
+```
+
+For more information, see the Nomic documentation on [Text embeddings](https://docs.nomic.ai/reference/endpoints/nomic-embed-text).