Update reusable component specs

ml6team · Nov 20, 2023 · 6bb9aa0 · 6bb9aa0
1 parent 3e5f45c
commit 6bb9aa0
Show file tree

Hide file tree

Showing 17 changed files with 95 additions and 150 deletions.
diff --git a/components/caption_images/fondant_component.yaml b/components/caption_images/fondant_component.yaml
@@ -5,16 +5,12 @@ tags:
   - Image processing
 
 consumes:
-  images:
-    fields:
-      data:
-        type: binary
+  images_data:
+    type: binary
 
 produces:
-  captions:
-    fields:
-      text:
-        type: utf8
+  captions_text:
+    type: utf8
 
 args:
   model_id:

diff --git a/components/chunk_text/fondant_component.yaml b/components/chunk_text/fondant_component.yaml
@@ -10,18 +10,14 @@ tags:
   - Text processing
 
 consumes:
-  text:
-    fields:
-      data:
-        type: string
+  text_data:
+    type: string
 
 produces:
-  text:
-    fields:
-      data:
-        type: string
-      original_document_id:
-        type: string
+  text_data:
+    type: string
+  text_original_document_id:
+    type: string
 
 args:
   chunk_size:

diff --git a/components/download_images/fondant_component.yaml b/components/download_images/fondant_component.yaml
@@ -13,20 +13,16 @@ tags:
   - Image processing
 
 consumes:
-  images:
-    fields:
-      url:
-        type: string
+  images_url:
+    type: string
 
 produces:
-  images:
-    fields:
-      data:
-        type: binary
-      width:
-        type: int32
-      height:
-        type: int32
+  images_data:
+    type: binary
+  images_width:
+    type: int32
+  images_height:
+    type: int32
     additionalFields: false
 
 args:
@@ -53,7 +49,7 @@ args:
     description: Resize mode to use. One of "no", "keep_ratio", "center_crop", "border".
     type: str
     default: 'border'
-  resize_only_if_bigger: 
+  resize_only_if_bigger:
     description: If True, resize only if image is bigger than image_size.
     type: bool
     default: False

diff --git a/components/embed_images/fondant_component.yaml b/components/embed_images/fondant_component.yaml
@@ -2,21 +2,17 @@ name: Embed images
 description: Component that generates CLIP embeddings from images
 image: fndnt/embed_images:dev
 tags:
-   - Image processing
+  - Image processing
 
 consumes:
-  images:
-      fields:
-        data:
-          type: binary
+  images_data:
+    type: binary
 
 produces:
-  embeddings:
-    fields:
-      data:
-        type: array
-        items:
-          type: float32
+  embeddings_data:
+    type: array
+    items:
+      type: float32
 
 args:
   model_id:

diff --git a/components/embed_text/fondant_component.yaml b/components/embed_text/fondant_component.yaml
@@ -5,21 +5,17 @@ tags:
   - Text processing
 
 consumes:
-  text:
-    fields:
-      data:
-        type: string
+  text_data:
+    type: string
 
 produces:
-  text:
-    fields:
-      data:
-        type: string
-      embedding:
-        type: array
-        items:
-          type: float32
-
+  text_data:
+    type: string
+  text_embedding:
+    type: array
+    items:
+      type: float32
+
 args:
   model_provider:
     description: |
@@ -40,12 +36,12 @@ args:
       Pass only the keys required by the model provider or conveniently pass all keys you will ever need. 
       Pay attention how to name the dictionary keys so that they can be used by the model provider.
     type: dict
-    default: {}
+    default: { }
   auth_kwargs:
     description: |
       Additional keyword arguments required for api initialization/authentication.
     type: dict
-    default: {}
+    default: { }
 
 
 
diff --git a/components/embedding_based_laion_retrieval/fondant_component.yaml b/components/embedding_based_laion_retrieval/fondant_component.yaml
@@ -7,18 +7,14 @@ tags:
   - Data retrieval
 
 consumes:
-  embeddings:
-    fields:
-      data:
-        type: array
-        items:
-          type: float32
+  embeddings_data:
+    type: array
+    items:
+      type: float32
 
 produces:
-  images:
-    fields:
-      url:
-        type: string
+  images_url:
+    type: string
   additionalSubsets: false
 
 args:

diff --git a/components/filter_image_resolution/fondant_component.yaml b/components/filter_image_resolution/fondant_component.yaml
@@ -5,12 +5,10 @@ tags:
   - Image processing
 
 consumes:
-  images:
-    fields:
-      width:
-        type: int32
-      height:
-        type: int32
+  images_width:
+    type: int32
+  images_height:
+    type: int32
 
 args:
   min_image_dim:

diff --git a/components/filter_text_length/fondant_component.yaml b/components/filter_text_length/fondant_component.yaml
@@ -5,10 +5,8 @@ tags:
   - Text processing
 
 consumes:
-  text:
-    fields:
-      data:
-        type: string
+  text_data:
+    type: string
 
 args:
   min_characters_length:

diff --git a/components/image_cropping/fondant_component.yaml b/components/image_cropping/fondant_component.yaml
@@ -20,20 +20,16 @@ tags:
   - Image processing
 
 consumes:
-  images:
-    fields:
-      data:
-        type: binary
+  images_data:
+    type: binary
 
 produces:
-  images:
-    fields:
-      data:
-        type: binary
-      width:
-        type: int32
-      height:
-        type: int32
+  images_data:
+    type: binary
+  images_width:
+    type: int32
+  images_height:
+    type: int32
 
 args:
   cropping_threshold:

diff --git a/components/image_resolution_extraction/fondant_component.yaml b/components/image_resolution_extraction/fondant_component.yaml
@@ -5,17 +5,13 @@ tags:
   - Image processing
 
 consumes:
-  images:
-    fields:
-      data:
-        type: binary
+  images_data:
+    type: binary
 
 produces:
-  images:
-    fields:
-      data:
-        type: binary
-      width:
-        type: int32
-      height:
-        type: int32
+  images_data:
+    type: binary
+  images_width:
+    type: int32
+  images_height:
+    type: int32
diff --git a/components/index_weaviate/fondant_component.yaml b/components/index_weaviate/fondant_component.yaml
@@ -5,14 +5,12 @@ tags:
   - Data writing
 
 consumes:
-  text:
-    fields:
-      data:
-        type: string
-      embedding:
-        type: array
-        items:
-          type: float32
+  text_data:
+    type: string
+  text_embedding:
+      type: array
+      items:
+        type: float32
 
 args:
   weaviate_url:

diff --git a/components/language_filter/fondant_component.yaml b/components/language_filter/fondant_component.yaml
@@ -5,10 +5,9 @@ tags:
   - Text processing
 
 consumes:
-  text:
-    fields:
-      data:
-        type: string
+  text_fields:
+    data:
+      type: string
 
 args:
   language:

diff --git a/components/load_from_files/fondant_component.yaml b/components/load_from_files/fondant_component.yaml
@@ -7,13 +7,11 @@ tags:
   - Data loading
 
 produces:
-  file:
-    fields:
-      filename:
-        type: string
-      content:
-        type: binary
-
+  file_filename:
+    type: string
+  file_content:
+    type: binary
+
 args:
   directory_uri:
     description: Local or remote path to the directory containing the files

diff --git a/components/minhash_generator/fondant_component.yaml b/components/minhash_generator/fondant_component.yaml
@@ -5,18 +5,14 @@ tags:
   - Text processing
 
 consumes:
-  text:
-    fields:
-      data:
-        type: string
+  text_data:
+    type: string
 
 produces:
-  text:
-    fields:
-      minhash:
-        type: array
-        items:
-            type: uint64
+  text_minhash:
+    type: array
+    items:
+      type: uint64
 args:
   shingle_ngram_size:
     description: Define size of ngram used for the shingle generation

diff --git a/components/normalize_text/fondant_component.yaml b/components/normalize_text/fondant_component.yaml
@@ -17,10 +17,8 @@ tags:
   - Text processing
 
 consumes:
-  text:
-    fields:
-      data:
-        type: string
+  text_data:
+    type: string
 
 args:
   remove_additional_whitespaces:

diff --git a/components/resize_images/fondant_component.yaml b/components/resize_images/fondant_component.yaml
@@ -5,16 +5,12 @@ tags:
   - Image processing
 
 consumes:
-  images:
-    fields:
-      data:
-        type: binary
+  images_data:
+    type: binary
 
 produces:
-  images:
-    fields:
-      data:
-        type: binary
+  images_data:
+    type: binary
 
 args:
   resize_width: