From 829d395ebe09ff974b5416f8c0eb6417ce8f59fd Mon Sep 17 00:00:00 2001
From: Anush <anushshetty90@gmail.com>
Date: Fri, 1 Mar 2024 00:35:24 +0530
Subject: [PATCH] docs: Added Nomic FastEmbed usage (#614)

---
 .../content/documentation/embeddings/nomic.md | 43 +++++++++++++++++--
 .../documentation/frameworks/fondant.md       |  2 +-
 2 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/qdrant-landing/content/documentation/embeddings/nomic.md b/qdrant-landing/content/documentation/embeddings/nomic.md
index c180cb8b7..6e181395e 100644
--- a/qdrant-landing/content/documentation/embeddings/nomic.md
+++ b/qdrant-landing/content/documentation/embeddings/nomic.md
@@ -8,12 +8,16 @@ weight: 1100
 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 find it easier to obtain them 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.
+Once installed, you can configure it with the official Python client, FastEmbed or through direct HTTP requests.
 
 <aside role="status">Using Nomic Text Embeddings requires configuring the Nomic API token</aside>
 
 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.
+are obtained for documents and queries.
+
+#### Upsert using [Nomic SDK](https://github.com/nomic-ai/nomic)
+
+The `task_type` parameter defines the embeddings that you get.
 For documents, set the `task_type` to `search_document`:
 
 ```python
@@ -36,6 +40,28 @@ qdrant_client.upsert(
 )
 ```
 
+#### Upsert using [FastEmbed](https://github.com/qdrant/fastembed)
+
+```python
+from fastembed import TextEmbedding
+from qdrant_client import QdrantClient, models
+
+model = TextEmbedding("nomic-ai/nomic-embed-text-v1")
+
+output = model.embed(["Qdrant is the best vector database!"])
+
+qdrant_client = QdrantClient()
+qdrant_client.upsert(
+    collection_name="my-collection",
+    points=models.Batch(
+        ids=[1],
+        vectors=[embeddings.tolist() for embeddings in output],
+    ),
+)
+```
+
+#### Search using [Nomic SDK](https://github.com/nomic-ai/nomic)
+
 To query the collection, set the `task_type` to `search_query`:
 
 ```python
@@ -47,7 +73,18 @@ output = embed.text(
 
 qdrant_client.search(
     collection_name="my-collection",
-    query=output["embeddings"][0],
+    query_vector=output["embeddings"][0],
+)
+```
+
+#### Search using [FastEmbed](https://github.com/qdrant/fastembed)
+
+```python
+output = next(model.embed("What is the best vector database?"))
+
+qdrant_client.search(
+    collection_name="my-collection",
+    query_vector=output.tolist(),
 )
 ```
 
diff --git a/qdrant-landing/content/documentation/frameworks/fondant.md b/qdrant-landing/content/documentation/frameworks/fondant.md
index e4bb2ea42..90995cdc4 100644
--- a/qdrant-landing/content/documentation/frameworks/fondant.md
+++ b/qdrant-landing/content/documentation/frameworks/fondant.md
@@ -18,7 +18,7 @@ pipeline, including a Qdrant component for writing embeddings to Qdrant.
 ## Usage
 
 <aside role="status">
-A Qdrant collection has to be <a href="documentation/concepts/collections/">created in advance</a>
+A Qdrant collection has to be <a href="/documentation/concepts/collections/">created in advance</a>
 </aside>
 
 **A data load pipeline for RAG using Qdrant**.