instill-ai · donch1989 · Dec 25, 2024 · Dec 25, 2024
@@ -80,9 +80,6 @@ component.
   "type": "COMPONENT_TYPE_OPERATOR",
   "description": "'Hello, world' operator used as a template for adding components",
   "spec": {},
-  "availableTasks": [
-    "TASK_GREET"
-  ],
   "documentationUrl": "https://www.instill.tech/docs/component/operator/hello",
   "icon": "assets/hello.svg",
   "version": "0.1.0",
@@ -103,10 +100,6 @@ This file defines the component properties:
 - **`spec`** contains the parameters required to configure the component and
   that are independent from its tasks. E.g., the API token of a vendor. In
   general, only AI, data or application components need such parameters.
-- **`availableTasks`** defines the tasks the component can perform.
-  - When a component is created in a pipeline, one of the tasks has to be
-    selected, i.e., a configured component can only execute one task.
-  - Task configurations are defined in `tasks.json`.
 - **`documentationUrl`** points to the official documentation of the component.
 - **`icon`** is the local path to the icon that will be displayed in the console
   when creating the component. If left blank, a placeholder icon will be shown.

@@ -1,5 +1,3 @@
-availableTasks:
-- TASK_TEXT_GENERATION_CHAT
 custom: false
 documentationUrl: https://www.instill.tech/docs/component/ai/anthropic
 icon: assets/anthropic.svg

@@ -7,8 +7,8 @@ description: "Learn about how to set up a VDP Cohere component https://github.co
 
 The Cohere component is an AI component that allows users to connect the AI models served on the Cohere Platform.
 It can carry out the following tasks:
-- [Text Generation Chat](#text-generation-chat)
 - [Text Embeddings](#text-embeddings)
+- [Text Generation Chat](#text-generation-chat)
 - [Text Reranking](#text-reranking)
 
 
@@ -50,6 +50,48 @@ ${connection.<my-connection-id>}`.
 
 ## Supported Tasks
 
+### Text Embeddings
+
+An embedding is a list of floating point numbers that captures semantic information about the text that it represents.
+
+<div class="markdown-col-no-wrap" data-col-1 data-col-2>
+
+| Input | Field ID | Format | Description |
+| :--- | :--- | :--- | :--- |
+| Task ID (required) | `task` | string | `TASK_TEXT_EMBEDDINGS` |
+| Embedding Type (required) | `embedding-type` | string | Specifies the return type of embedding, Note that 'binary'/'ubinary' options means the component will return packed unsigned binary embeddings. The length of each binary embedding is 1/8 the length of the float embeddings of the provided model. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`float`</li><li>`int8`</li><li>`uint8`</li><li>`binary`</li><li>`ubinary`</li></ul></details>  |
+| Input Type (required) | `input-type` | string | Specifies the type of input passed to the model. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`search_document`</li><li>`search_query`</li><li>`classification`</li><li>`clustering`</li></ul></details>  |
+| Model Name (required) | `model-name` | string | The Cohere embed model to be used. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`embed-english-v3.0`</li><li>`embed-multilingual-v3.0`</li><li>`embed-english-light-v3.0`</li><li>`embed-multilingual-light-v3.0`</li></ul></details>  |
+| Text (required) | `text` | string | The text. |
+</div>
+
+
+
+
+
+
+<div class="markdown-col-no-wrap" data-col-1 data-col-2>
+
+| Output | Field ID | Format | Description |
+| :--- | :--- | :--- | :--- |
+| Embedding | `embedding` | array[number] | Embedding of the input text. |
+| [Usage](#text-embeddings-usage) (optional) | `usage` | object | Token usage on the Cohere platform embed models. |
+</div>
+
+<details>
+<summary> Output Objects in Text Embeddings</summary>
+
+<h4 id="text-embeddings-usage">Usage</h4>
+
+<div class="markdown-col-no-wrap" data-col-1 data-col-2>
+
+| Field | Field ID | Format | Note |
+| :--- | :--- | :--- | :--- |
+| Token Count | `tokens` | number | The token count used by Cohere Models. |
+</div>
+</details>
+
+
 ### Text Generation Chat
 
 Cohere's text generation models (often called generative pre-trained transformers or large language models) have been trained to understand natural language, code, and images. The models provide text outputs in response to their inputs. The inputs to these models are also referred to as "prompts". Designing a prompt is essentially how you “program” a large language model model, usually by providing instructions or some examples of how to successfully complete a task.
@@ -147,48 +189,6 @@ The image URL.
 </details>
 
 
-### Text Embeddings
-
-An embedding is a list of floating point numbers that captures semantic information about the text that it represents.
-
-<div class="markdown-col-no-wrap" data-col-1 data-col-2>
-
-| Input | Field ID | Format | Description |
-| :--- | :--- | :--- | :--- |
-| Task ID (required) | `task` | string | `TASK_TEXT_EMBEDDINGS` |
-| Embedding Type (required) | `embedding-type` | string | Specifies the return type of embedding, Note that 'binary'/'ubinary' options means the component will return packed unsigned binary embeddings. The length of each binary embedding is 1/8 the length of the float embeddings of the provided model. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`float`</li><li>`int8`</li><li>`uint8`</li><li>`binary`</li><li>`ubinary`</li></ul></details>  |
-| Input Type (required) | `input-type` | string | Specifies the type of input passed to the model. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`search_document`</li><li>`search_query`</li><li>`classification`</li><li>`clustering`</li></ul></details>  |
-| Model Name (required) | `model-name` | string | The Cohere embed model to be used. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`embed-english-v3.0`</li><li>`embed-multilingual-v3.0`</li><li>`embed-english-light-v3.0`</li><li>`embed-multilingual-light-v3.0`</li></ul></details>  |
-| Text (required) | `text` | string | The text. |
-</div>
-
-
-
-
-
-
-<div class="markdown-col-no-wrap" data-col-1 data-col-2>
-
-| Output | Field ID | Format | Description |
-| :--- | :--- | :--- | :--- |
-| Embedding | `embedding` | array[number] | Embedding of the input text. |
-| [Usage](#text-embeddings-usage) (optional) | `usage` | object | Token usage on the Cohere platform embed models. |
-</div>
-
-<details>
-<summary> Output Objects in Text Embeddings</summary>
-
-<h4 id="text-embeddings-usage">Usage</h4>
-
-<div class="markdown-col-no-wrap" data-col-1 data-col-2>
-
-| Field | Field ID | Format | Note |
-| :--- | :--- | :--- | :--- |
-| Token Count | `tokens` | number | The token count used by Cohere Models. |
-</div>
-</details>
-
-
 ### Text Reranking
 
 Rerank models sort text inputs by semantic relevance to a specified query. They are often used to sort search results returned from an existing search solution.

@@ -1,7 +1,3 @@
-availableTasks:
-- TASK_TEXT_GENERATION_CHAT
-- TASK_TEXT_EMBEDDINGS
-- TASK_TEXT_RERANKING
 documentationUrl: https://www.instill.tech/docs/component/ai/cohere
 icon: assets/cohere.svg
 id: cohere

@@ -7,8 +7,8 @@ description: "Learn about how to set up a VDP Fireworks AI component https://git
 
 The Fireworks AI component is an AI component that allows users to connect the AI models served on the Fireworks AI Platform.
 It can carry out the following tasks:
-- [Text Generation Chat](#text-generation-chat)
 - [Text Embeddings](#text-embeddings)
+- [Text Generation Chat](#text-generation-chat)
 
 
 
@@ -49,6 +49,46 @@ ${connection.<my-connection-id>}`.
 
 ## Supported Tasks
 
+### Text Embeddings
+
+An embedding is a list of floating point numbers that captures semantic information about the text that it represents.
+
+<div class="markdown-col-no-wrap" data-col-1 data-col-2>
+
+| Input | Field ID | Format | Description |
+| :--- | :--- | :--- | :--- |
+| Task ID (required) | `task` | string | `TASK_TEXT_EMBEDDINGS` |
+| Model Name (required) | `model` | string | The OSS embedding model to be used. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`nomic-ai/nomic-embed-text-v1.5`</li><li>`nomic-ai/nomic-embed-text-v1`</li><li>`WhereIsAI/UAE-Large-V1`</li><li>`thenlper/gte-large`</li><li>`thenlper/gte-base`</li></ul></details>  |
+| Text (required) | `text` | string | The text. |
+</div>
+
+
+
+
+
+
+<div class="markdown-col-no-wrap" data-col-1 data-col-2>
+
+| Output | Field ID | Format | Description |
+| :--- | :--- | :--- | :--- |
+| Embedding | `embedding` | array[number] | Embedding of the input text. |
+| [Usage](#text-embeddings-usage) (optional) | `usage` | object | Token usage on the Fireworks AI platform embedding models. |
+</div>
+
+<details>
+<summary> Output Objects in Text Embeddings</summary>
+
+<h4 id="text-embeddings-usage">Usage</h4>
+
+<div class="markdown-col-no-wrap" data-col-1 data-col-2>
+
+| Field | Field ID | Format | Note |
+| :--- | :--- | :--- | :--- |
+| Token Count | `tokens` | number | The token count used by Fireworks AI models. |
+</div>
+</details>
+
+
 ### Text Generation Chat
 
 Fireworks AI's text generation models (often called generative pre-trained transformers or large language models) have been trained to understand natural language, code, and images. The models provide text outputs in response to their inputs. The inputs to these models are also referred to as "prompts". Designing a prompt is essentially how you “program” a large language model model, usually by providing instructions or some examples of how to successfully complete a task.
@@ -134,46 +174,6 @@ The image URL.
 </details>
 
 
-### Text Embeddings
-
-An embedding is a list of floating point numbers that captures semantic information about the text that it represents.
-
-<div class="markdown-col-no-wrap" data-col-1 data-col-2>
-
-| Input | Field ID | Format | Description |
-| :--- | :--- | :--- | :--- |
-| Task ID (required) | `task` | string | `TASK_TEXT_EMBEDDINGS` |
-| Model Name (required) | `model` | string | The OSS embedding model to be used. <br/><details><summary><strong>Enum values</strong></summary><ul><li>`nomic-ai/nomic-embed-text-v1.5`</li><li>`nomic-ai/nomic-embed-text-v1`</li><li>`WhereIsAI/UAE-Large-V1`</li><li>`thenlper/gte-large`</li><li>`thenlper/gte-base`</li></ul></details>  |
-| Text (required) | `text` | string | The text. |
-</div>
-
-
-
-
-
-
-<div class="markdown-col-no-wrap" data-col-1 data-col-2>
-
-| Output | Field ID | Format | Description |
-| :--- | :--- | :--- | :--- |
-| Embedding | `embedding` | array[number] | Embedding of the input text. |
-| [Usage](#text-embeddings-usage) (optional) | `usage` | object | Token usage on the Fireworks AI platform embedding models. |
-</div>
-
-<details>
-<summary> Output Objects in Text Embeddings</summary>
-
-<h4 id="text-embeddings-usage">Usage</h4>
-
-<div class="markdown-col-no-wrap" data-col-1 data-col-2>
-
-| Field | Field ID | Format | Note |
-| :--- | :--- | :--- | :--- |
-| Token Count | `tokens` | number | The token count used by Fireworks AI models. |
-</div>
-</details>
-
-
 
 ## Example Recipes
 

@@ -1,6 +1,3 @@
-availableTasks:
-- TASK_TEXT_GENERATION_CHAT
-- TASK_TEXT_EMBEDDINGS
 custom: false
 documentationUrl: https://www.instill.tech/docs/component/ai/fireworks-ai
 icon: assets/fireworks-ai.svg

@@ -1,5 +1,3 @@
-availableTasks:
-- TASK_TEXT_GENERATION_CHAT
 documentationUrl: https://www.instill.tech/docs/component/ai/groq
 icon: assets/groq.svg
 id: groq