diff --git a/qdrant-landing/content/documentation/tutorials/contract-management-stackit-aleph-alpha.md b/qdrant-landing/content/documentation/tutorials/contract-management-stackit-aleph-alpha.md index 1f4fe630e..1f61877cb 100644 --- a/qdrant-landing/content/documentation/tutorials/contract-management-stackit-aleph-alpha.md +++ b/qdrant-landing/content/documentation/tutorials/contract-management-stackit-aleph-alpha.md @@ -14,7 +14,7 @@ Companies want their data to be kept and processed within specific geographical [//]: # (TODO: add link to Qdrant Hybrid Cloud above) -TODO: add a system diagram with all the components +![Architecture diagram](/documentation/tutorials/contract-management-stackit-aleph-alpha/architecture-diagram.png) ## Components @@ -25,9 +25,7 @@ Directory. > **Note:** In this tutorial, we are going to build a solid foundation for such a system. However, it is up to your organization's setup to implement the entire solution. -[//]: # (TODO: upload the dataset to GCP and link it below) - -- **Dataset** - a collection of documents, using different formats, such as PDF or DOCx +- **Dataset** - a collection of documents, using different formats, such as PDF or DOCx, scraped from internet - **Asymmetric semantic embeddings** - [Aleph Alpha embedding](https://docs.aleph-alpha.com/api/semantic-embed/) to convert the queries and the documents into vectors - **Large Language Model** - the [Luminous-extended-control @@ -155,6 +153,10 @@ documents = { } ``` +This is how the documents might look like: + +![Example of the indexed document](/documentation/tutorials/contract-management-stackit-aleph-alpha/indexed-document.png) + Each has to be split into chunks first; there is no silver bullet. Our chunking algorithm will be simple and based on recursive splitting, with the maximum chunk size of 500 characters and the overlap of 100 characters. diff --git a/qdrant-landing/static/documentation/tutorials/contract-management-stackit-aleph-alpha/architecture-diagram.png b/qdrant-landing/static/documentation/tutorials/contract-management-stackit-aleph-alpha/architecture-diagram.png new file mode 100644 index 000000000..2495ce57c Binary files /dev/null and b/qdrant-landing/static/documentation/tutorials/contract-management-stackit-aleph-alpha/architecture-diagram.png differ diff --git a/qdrant-landing/static/documentation/tutorials/contract-management-stackit-aleph-alpha/indexed-document.png b/qdrant-landing/static/documentation/tutorials/contract-management-stackit-aleph-alpha/indexed-document.png new file mode 100644 index 000000000..24c49efa5 Binary files /dev/null and b/qdrant-landing/static/documentation/tutorials/contract-management-stackit-aleph-alpha/indexed-document.png differ