Add descriptions for all code snippets

qdrant-landing/content/documentation/headless/snippets/inference/cohere/_description.md

@@ -0,0 +1 @@
+This code snippet demonstrates how to use the Cohere API for inference on Qdrant Cloud. The example first creates a collection that supports vectors with 512 dimensions. Next, a point is inserted, but instead of providing an explicit vector, the example request includes text along with the name of an Cohere model. When the model name is prepended with `cohere/`, the Qdrant Cloud Inference proxy will use the Cohere API to infer embeddings out of the provided text and store the resulting vector. The request also shows how to pass Cohere-specific parameters to the API. In this case, the request passes the Cohere API key and the `dimensions` parameter. Finally, the example shows how to use the Cohere API for query-time inference. Instead of supplying an explicit query vector, the query includes text and name of an Cohere model, as well as an Cohere API key and the Cohere-specific `dimensions` parameter. When the model name is prepended with `cohere/`, the Qdrant Cloud Inference proxy will use the Cohere API to infer embeddings out of the provided text and search with the resulting vector.

qdrant-landing/content/documentation/headless/snippets/inference/create-512-dims/http.md

@@ -1,9 +0,0 @@
-```http
-PUT /collections/<your-collection_name>
-{
-  "vectors": {
-    "size": 512,
-    "distance": "Cosine"
-  }
-}
-```

qdrant-landing/content/documentation/headless/snippets/inference/ingest/_description.md

@@ -0,0 +1 @@
+This code snippet shows how to use inference at ingest time. The example ingests a single point into a collection. Instead of providing an explicit vector, the request includes `text` and a `model`. Qdrant will use the model to infer embeddings out of the provided text and store the resulting vector.

qdrant-landing/content/documentation/headless/snippets/inference/jinaai/_description.md

@@ -0,0 +1 @@
+This code snippet demonstrates how to use the Jina AI API for inference on Qdrant Cloud. The example first creates a collection that supports vectors with 512 dimensions. Next, a point is inserted, but instead of providing an explicit vector, the example request includes text along with the name of an Jina AI model. When the model name is prepended with `jinaai/`, the Qdrant Cloud Inference proxy will use the Jina AI API to infer embeddings out of the provided text and store the resulting vector. The request also shows how to pass Jina AI-specific parameters to the API. In this case, the request passes the Jina AI API key and the `dimensions` parameter. Finally, the example shows how to use the Jina AI API for query-time inference. Instead of supplying an explicit query vector, the query includes text and name of an Jina AI model, as well as an Jina AI API key and the Jina AI-specific `dimensions` parameter. When the model name is prepended with `jinaai/`, the Qdrant Cloud Inference proxy will use the Jina AI API to infer embeddings out of the provided text and search with the resulting vector.

qdrant-landing/content/documentation/headless/snippets/inference/multiple/_description.md

@@ -0,0 +1 @@
+This code snippet shows how to run multiple inference operations within a single request, even when models are hosted in different locations. The request generates three different named vectors for a single point: image embeddings using `jina-clip-v2` hosted by Jina AI, text embeddings using `all-minilm-l6-v2` hosted by Qdrant Cloud, and BM25 embeddings using the `bm25` model executed locally by the Qdrant cluster.

qdrant-landing/content/documentation/headless/snippets/inference/openai/_description.md

@@ -0,0 +1 @@
+This code snippet demonstrates how to use the OpenAI API for inference on Qdrant Cloud. The example first creates a collection that supports vectors with 512 dimensions. Next, a point is inserted, but instead of providing an explicit vector, the example request includes text along with the name of an OpenAI model. When the model name is prepended with `openai/`, the Qdrant Cloud Inference proxy will use the OpenAI API to infer embeddings out of the provided text and store the resulting vector. The request also shows how to pass OpenAI-specific parameters to the API. In this case, the request passes the OpenAI API key and the `dimensions` parameter. Finally, the example shows how to use the OpenAI API for query-time inference. Instead of supplying an explicit query vector, the query includes text and name of an OpenAI model, as well as an OpenAI API key and the OpenAI-specific `dimensions` parameter. When the model name is prepended with `openai/`, the Qdrant Cloud Inference proxy will use the OpenAI API to infer embeddings out of the provided text and search with the resulting vector.

qdrant-landing/content/documentation/headless/snippets/inference/query/_description.md

@@ -0,0 +1 @@
+This code snippet shows how to use inference at query time. The example queries a collection. Instead of providing an explicit query vector, the request includes `text` and a `model`. Qdrant will use the model to infer embeddings out of the provided text and search with the resulting vector.