diff --git a/docs/src/content/docs/reference/helm-chart-config.mdx b/docs/src/content/docs/reference/helm-chart-config.mdx index 22bb1c09e..84938e0d6 100644 --- a/docs/src/content/docs/reference/helm-chart-config.mdx +++ b/docs/src/content/docs/reference/helm-chart-config.mdx @@ -76,7 +76,12 @@ Definition of metadata fields for sequence entries of an organism, for example t The values for `args` and `configFile` depend on the used preprocessing pipeline. -For the Nextclade preprocessing pipeline, please see + +#### Nextclade Preprocessing Pipeline ConfigFile (type) + + + +For more details on the Nextclade preprocessing pipeline, please see [here](../../for-administrators/existing-preprocessing-pipelines/#nextclade-based-pipeline). ### Ingest (type) @@ -84,11 +89,12 @@ For the Nextclade preprocessing pipeline, please see The values for `configFile` depend on the used preprocessing pipeline. -For [our ingest pipeline](https://github.com/loculus-project/loculus/tree/main/ingest) -which downloads data from NCBI GenBank using NCBI Datasets, the config file needs to -contain the taxon_id of the organism and additionally, if the organism is multi-segmented, -it requires a list of segment names (nucleotide_sequences) and the nextclade_dataset that -can be used for segment identification and alignment. + +#### Ingest ConfigFile (type) + +For [our ingest pipeline](https://github.com/loculus-project/loculus/tree/main/ingest) we require the following fields: + + ### NucleotideSequence (type) diff --git a/kubernetes/loculus/values.schema.json b/kubernetes/loculus/values.schema.json index 93802fe2a..242433743 100644 --- a/kubernetes/loculus/values.schema.json +++ b/kubernetes/loculus/values.schema.json @@ -335,19 +335,19 @@ "description": "Fields that should be added to the preprocessing pipeline config file.", "properties": { "alignment_requirement": { - "groups": ["ingest"], + "groups": ["nextcladePipelineConfigFile"], "docsIncludePrefix": false, "type": "string", "enum": ["ALL", "ANY"], "description": "If multi-segmented viruses should require ALL segments align or ANY segment aligns" }, "nextclade_dataset_server": { - "groups": ["ingest"], + "groups": ["nextcladePipelineConfigFile"], "docsIncludePrefix": false, "type": "string" }, "nextclade_dataset_name": { - "groups": ["ingest"], + "groups": ["nextcladePipelineConfigFile"], "docsIncludePrefix": false, "type": "string", "description": "Required if sequences should be aligned" @@ -391,31 +391,31 @@ "description": "If multi-segmented organism, how to identify segments", "properties": { "method": { - "groups": ["ingest"], + "groups": ["ingestPipelineConfigFile"], "docsIncludePrefix": false, "type": "string", "enum": ["align", "minimizer"], "description": "Method to identify segments, uses either nextclade align or nextclade sort" }, "nextclade_dataset_server": { - "groups": ["ingest"], + "groups": ["ingestPipelineConfigFile"], "docsIncludePrefix": false, "type": "string" }, "nextclade_dataset_name": { - "groups": ["ingest"], + "groups": ["ingestPipelineConfigFile"], "docsIncludePrefix": false, "type": "string", "description": "Required if method is align" }, "minimizer_parser": { - "groups": ["ingest"], + "groups": ["ingestPipelineConfigFile"], "docsIncludePrefix": false, "type": "array", "description": "Required if method is minimizer, list of the name of each '_' - separated metadata field in the minimizer index" }, "minimizer_index": { - "groups": ["ingest"], + "groups": ["ingestPipelineConfigFile"], "docsIncludePrefix": false, "type": "string", "description": "Required if method is minimizer"