krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-29 07:58:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: broken links, images (#475)

Browse Source 
* fix: broken links, images

* fix: aliases
This commit is contained in:
Anush
2023-12-17 23:25:07 +00:00
committed by GitHub
parent b99735dbb9
commit 64e6bb66e2
20 changed files with 29 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/frameworks/airbyte.md
+7 -7
View File
@@ -1,7 +1,7 @@
---
title: Airbyte
weight: 1000
aliases: [ /integrations/airbyte/ ]
aliases: [ ../integrations/airbyte/ ]
---
# Airbyte
@@ -34,7 +34,7 @@ Before you start, make sure you have the following:
Once you have a running instance of Airbyte, you can set up Qdrant as a destination directly in the UI.
Airbyte's Qdrant destination is connected with a single collection in Qdrant.
![Airbyte Qdrant destination](/documentation/integrations/airbyte/qdrant-destination.png)
![Airbyte Qdrant destination](/documentation/frameworks/airbyte/qdrant-destination.png)
### Text processing
@@ -42,26 +42,26 @@ Airbyte has some built-in mechanisms to transform your texts into embeddings. Yo
chunk your fields into pieces before calculating the embeddings, but also which fields should be used to
create the point payload.
![Processing settings](/documentation/integrations/airbyte/processing.png)
![Processing settings](/documentation/frameworks/airbyte/processing.png)
### Embeddings
You can choose the model that will be used to calculate the embeddings. Currently, Airbyte supports multiple
models, including OpenAI and Cohere.
![Embeddings settings](/documentation/integrations/airbyte/embedding.png)
![Embeddings settings](/documentation/frameworks/airbyte/embedding.png)
Using some precomputed embeddings from your data source is also possible. In this case, you can pass the field
name containing the embeddings and their dimensionality.
![Precomputed embeddings settings](/documentation/integrations/airbyte/precomputed-embedding.png)
![Precomputed embeddings settings](/documentation/frameworks/airbyte/precomputed-embedding.png)
### Qdrant connection details
Finally, we can configure the target Qdrant instance and collection. In case you use the built-in authentication
mechanism, here is where you can pass the token.
![Qdrant connection details](/documentation/integrations/airbyte/qdrant-config.png)
![Qdrant connection details](/documentation/frameworks/airbyte/qdrant-config.png)
Once you confirm creating the destination, Airbyte will test if a specified Qdrant cluster is accessible and
might be used as a destination.
@@ -72,7 +72,7 @@ Airbyte combines sources and destinations into a single entity called a connecti
configured and a source, you can create a connection between them. It doesn't matter what source you use, as
long as Airbyte supports it. The process is pretty straightforward, but depends on the source you use.
![Airbyte connection](/documentation/integrations/airbyte/connection.png)
![Airbyte connection](/documentation/frameworks/airbyte/connection.png)
More information about creating connections can be found in the
[Airbyte documentation](https://docs.airbyte.com/understanding-airbyte/connections/).