Required parameters

When deploying the ADLS to Chroma DB [Technical Preview] ReadyFlow, you have to provide the following parameters. Use the information you collected in Prerequisites.

Table 1. ADLS to Chroma DB [Technical Preview] ReadyFlow configuration parameters
Parameter Name Description
CDP Workload User Specify the Cloudera machine user or workload username that you want to use to authenticate to the object stores (via IDBroker). Ensure this user has the appropriate access rights to the object store locations.
CDP Workload User Password Specify the password of the Cloudera machine user or workload user you are using to authenticate against the object stores (via IDBroker).
CDPEnvironment The Cloudera Environment configuration resources.
Chroma Collection Name Specify the name of the Chroma collection to write to.
Chroma Server Authentication Token Specify the authentication token used to authenticate to Chroma.
Chroma Server Hostname Specify the Chroma server host name.
Chroma Server Port Specify the Chroma server port. The default value is "443".
OpenAI API Key Specify the API key used to authenticate to OpenAI.
OpenAI Model Name Specify the OpenAI model name to use for embedding the data.

The default model is 'text-embedding-ada-002'.

Source ADLS File System Specify the name of the ADLS data container you want to read from. The full path will be constructed from: abfs://#{Source ADLS File System}@#{Source ADLS Storage Account}.dfs.core.windows.net/#{Source ADLS Path}
Source ADLS Path Specify the path within the ADLS data container where you want to read from without any leading characters. The full path will be constructed from: abfs://#{Source ADLS File System}@#{Source ADLS Storage Account}.dfs.core.windows.net/#{Source ADLS Path}
Source ADLS Storage Account Specify the source ADLS storage account name.