[Inference API] Add image-text-to-text task and fix generate script

docs/api-inference/_toctree.yml

@@ -30,6 +30,8 @@
       title: Image Segmentation
     - local: tasks/image-to-image
       title: Image to Image
+    - local: tasks/image-text-to-text
+      title: Image-Text to Text
     - local: tasks/object-detection
       title: Object Detection
     - local: tasks/question-answering

docs/api-inference/tasks/audio-classification.md

@@ -43,7 +43,6 @@ curl https://api-inference.huggingface.co/models/<REPO_ID> \
 	-X POST \
 	--data-binary '@sample1.flac' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/automatic-speech-recognition.md

@@ -30,6 +30,7 @@ For more details about the `automatic-speech-recognition` task, check out its [d
 ### Recommended models
 
 - [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3): A powerful ASR model by OpenAI.
+- [facebook/seamless-m4t-v2-large](https://huggingface.co/facebook/seamless-m4t-v2-large): An end-to-end model that performs ASR and Speech Translation by MetaAI.
 - [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1): Powerful speaker diarization model.
 
 This is only a subset of the supported models. Find the model that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=automatic-speech-recognition&sort=trending).
@@ -45,7 +46,6 @@ curl https://api-inference.huggingface.co/models/openai/whisper-large-v3 \
 	-X POST \
 	--data-binary '@sample1.flac' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 
@@ -108,7 +108,7 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/
 | **inputs*** | _string_ | The input audio data as a base64-encoded string. If no `parameters` are provided, you can also provide the audio data as a raw bytes payload. |
 | **parameters** | _object_ | Additional inference parameters for Automatic Speech Recognition |
 | **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;return_timestamps** | _boolean_ | Whether to output corresponding timestamps with the generated text |
-| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generate** | _object_ | Ad-hoc parametrization of the text generation process |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;generation_parameters** | _object_ | Ad-hoc parametrization of the text generation process |
 | **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;temperature** | _number_ | The value used to modulate the next token probabilities. |
 | **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k** | _integer_ | The number of highest probability vocabulary tokens to keep for top-k-filtering. |
 | **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_p** | _number_ | If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation. |

docs/api-inference/tasks/chat-completion.md

@@ -59,18 +59,15 @@ curl 'https://api-inference.huggingface.co/models/google/gemma-2-2b-it/v1/chat/c
 ```py
 from huggingface_hub import InferenceClient
 
-client = InferenceClient(
-    "google/gemma-2-2b-it",
-    token="hf_***",
-)
+client = InferenceClient(api_key="hf_***")
 
 for message in client.chat_completion(
+	model="google/gemma-2-2b-it",
 	messages=[{"role": "user", "content": "What is the capital of France?"}],
 	max_tokens=500,
 	stream=True,
 ):
     print(message.choices[0].delta.content, end="")
-
 ```
 
 To use the Python client, see `huggingface_hub`'s [package reference](https://huggingface.co/docs/huggingface_hub/package_reference/inference_client#huggingface_hub.InferenceClient.chat_completion).
@@ -89,7 +86,6 @@ for await (const chunk of inference.chatCompletionStream({
 })) {
 	process.stdout.write(chunk.choices[0]?.delta?.content || "");
 }
-
 ```
 
 To use the JavaScript client, see `huggingface.js`'s [package reference](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference#chatcompletion).

docs/api-inference/tasks/feature-extraction.md

@@ -45,7 +45,6 @@ curl https://api-inference.huggingface.co/models/thenlper/gte-large \
 	-d '{"inputs": "Today is a sunny day and I will get some ice cream."}' \
 	-H 'Content-Type: application/json' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/fill-mask.md

@@ -41,7 +41,6 @@ curl https://api-inference.huggingface.co/models/google-bert/bert-base-uncased \
 	-d '{"inputs": "The answer to the universe is [MASK]."}' \
 	-H 'Content-Type: application/json' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/image-classification.md

@@ -39,7 +39,6 @@ curl https://api-inference.huggingface.co/models/google/vit-base-patch16-224 \
 	-X POST \
 	--data-binary '@cats.jpg' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/image-segmentation.md

@@ -39,7 +39,6 @@ curl https://api-inference.huggingface.co/models/nvidia/segformer-b0-finetuned-a
 	-X POST \
 	--data-binary '@cats.jpg' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/image-text-to-text.md

@@ -0,0 +1,129 @@
+<!---
+This markdown file has been generated from a script. Please do not edit it directly.
+For more details, check out:
+- the `generate.ts` script: https://github.com/huggingface/hub-docs/blob/main/scripts/api-inference/scripts/generate.ts
+- the task template defining the sections in the page: https://github.com/huggingface/hub-docs/tree/main/scripts/api-inference/templates/task/image-text-to-text.handlebars
+- the input jsonschema specifications used to generate the input markdown table: https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/src/tasks/image-text-to-text/spec/input.json
+- the output jsonschema specifications used to generate the output markdown table: https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/src/tasks/image-text-to-text/spec/output.json
+- the snippets used to generate the example:
+  - curl: https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/src/snippets/curl.ts
+  - python: https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/src/snippets/python.ts
+  - javascript: https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/src/snippets/js.ts
+- the "tasks" content for recommended models: https://huggingface.co/api/tasks
+--->
+
+## Image-Text to Text
+
+Image-text-to-text models take in an image and text prompt and output text. These models are also called vision-language models, or VLMs. The difference from image-to-text models is that these models take an additional text input, not restricting the model to certain use cases like image captioning, and may also be trained to accept a conversation as input.
+
+<Tip>
+
+For more details about the `image-text-to-text` task, check out its [dedicated page](https://huggingface.co/tasks/image-text-to-text)! You will find examples and related materials.
+
+</Tip>
+
+### Recommended models
+
+- [HuggingFaceM4/idefics2-8b-chatty](https://huggingface.co/HuggingFaceM4/idefics2-8b-chatty): Cutting-edge conversational vision language model that can take multiple image inputs.
+- [microsoft/Phi-3.5-vision-instruct](https://huggingface.co/microsoft/Phi-3.5-vision-instruct): Strong image-text-to-text model.
+
+This is only a subset of the supported models. Find the model that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=image-text-to-text&sort=trending).
+
+### Using the API
+
+
+<inferencesnippet>
+
+<curl>
+```bash
+curl https://api-inference.huggingface.co/models/HuggingFaceM4/idefics2-8b-chatty \
+	-X POST \
+	-d '{"inputs": No input example has been defined for this model task.}' \
+	-H 'Content-Type: application/json' \
+	-H "Authorization: Bearer hf_***"
+```
+</curl>
+
+<python>
+```py
+import requests
+
+API_URL = "https://api-inference.huggingface.co/models/HuggingFaceM4/idefics2-8b-chatty"
+headers = {"Authorization": "Bearer hf_***"}
+
+from huggingface_hub import InferenceClient
+
+client = InferenceClient(api_key="hf_***")
+
+image_url = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
+
+for message in client.chat_completion(
+	model="HuggingFaceM4/idefics2-8b-chatty",
+	messages=[
+		{
+			"role": "user",
+			"content": [
+				{"type": "image_url", "image_url": {"url": image_url}},
+				{"type": "text", "text": "Describe this image in one sentence."},
+			],
+		}
+	],
+	max_tokens=500,
+	stream=True,
+):
+	print(message.choices[0].delta.content, end="")
+```
+
+To use the Python client, see `huggingface_hub`'s [package reference](https://huggingface.co/docs/huggingface_hub/package_reference/inference_client#huggingface_hub.InferenceClient.image_text-to-text).
+</python>
+
+<js>
+```js
+async function query(data) {
+	const response = await fetch(
+		"https://api-inference.huggingface.co/models/HuggingFaceM4/idefics2-8b-chatty",
+		{
+			headers: {
+				Authorization: "Bearer hf_***"
+				"Content-Type": "application/json",
+			},
+			method: "POST",
+			body: JSON.stringify(data),
+		}
+	);
+	const result = await response.json();
+	return result;
+}
+
+query({"inputs": No input example has been defined for this model task.}).then((response) => {
+	console.log(JSON.stringify(response));
+});
+```
+
+To use the JavaScript client, see `huggingface.js`'s [package reference](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference#imagetext-to-text).
+</js>
+
+</inferencesnippet>
+
+
+
+### API specification
+
+#### Request
+
+
+
+Some options can be configured by passing headers to the Inference API. Here are the available headers:
+
+| Headers |   |    |
+| :--- | :--- | :--- |
+| **authorization** | _string_ | Authentication header in the form `'Bearer: hf_****'` when `hf_****` is a personal user access token with Inference API permission. You can generate one from [your settings page](https://huggingface.co/settings/tokens). |
+| **x-use-cache** | _boolean, default to `true`_ | There is a cache layer on the inference API to speed up requests we have already seen. Most models can use those results as they are deterministic (meaning the outputs will be the same anyway). However, if you use a nondeterministic model, you can set this parameter to prevent the caching mechanism from being used, resulting in a real new query. Read more about caching [here](../parameters#caching]). |
+| **x-wait-for-model** | _boolean, default to `false`_ | If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error, as it will limit hanging in your application to known places. Read more about model availability [here](../overview#eligibility]). |
+
+For more information about Inference API headers, check out the parameters [guide](../parameters).
+
+#### Response
+
+
+

docs/api-inference/tasks/object-detection.md

@@ -40,7 +40,6 @@ curl https://api-inference.huggingface.co/models/facebook/detr-resnet-50 \
 	-X POST \
 	--data-binary '@cats.jpg' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/question-answering.md

@@ -26,6 +26,7 @@ For more details about the `question-answering` task, check out its [dedicated p
 
 - [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2): A robust baseline model for most question answering domains.
 - [distilbert/distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert/distilbert-base-cased-distilled-squad): Small yet robust model that can answer questions.
+- [google/tapas-base-finetuned-wtq](https://huggingface.co/google/tapas-base-finetuned-wtq): A special model that can answer questions from tables.
 
 This is only a subset of the supported models. Find the model that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=question-answering&sort=trending).
 
@@ -41,7 +42,6 @@ curl https://api-inference.huggingface.co/models/deepset/roberta-base-squad2 \
 	-d '{"inputs": { "question": "What is my name?", "context": "My name is Clara and I live in Berkeley." }}' \
 	-H 'Content-Type: application/json' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/summarization.md

@@ -40,7 +40,6 @@ curl https://api-inference.huggingface.co/models/facebook/bart-large-cnn \
 	-d '{"inputs": "The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct."}' \
 	-H 'Content-Type: application/json' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/table-question-answering.md

@@ -24,6 +24,7 @@ For more details about the `table-question-answering` task, check out its [dedic
 
 ### Recommended models
 
+- [google/tapas-base-finetuned-wtq](https://huggingface.co/google/tapas-base-finetuned-wtq): A robust table question answering model.
 
 This is only a subset of the supported models. Find the model that suits you best [here](https://huggingface.co/models?inference=warm&pipeline_tag=table-question-answering&sort=trending).
 
@@ -34,20 +35,19 @@ This is only a subset of the supported models. Find the model that suits you bes
 
 <curl>
 ```bash
-curl https://api-inference.huggingface.co/models/<REPO_ID> \
+curl https://api-inference.huggingface.co/models/google/tapas-base-finetuned-wtq \
 	-X POST \
 	-d '{"inputs": { "query": "How many stars does the transformers repository have?", "table": { "Repository": ["Transformers", "Datasets", "Tokenizers"], "Stars": ["36542", "4512", "3934"], "Contributors": ["651", "77", "34"], "Programming language": [ "Python", "Python", "Rust, Python and NodeJS" ] } }}' \
 	-H 'Content-Type: application/json' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 
 <python>
 ```py
 import requests
 
-API_URL = "https://api-inference.huggingface.co/models/<REPO_ID>"
+API_URL = "https://api-inference.huggingface.co/models/google/tapas-base-finetuned-wtq"
 headers = {"Authorization": "Bearer hf_***"}
 
 def query(payload):
@@ -78,7 +78,7 @@ To use the Python client, see `huggingface_hub`'s [package reference](https://hu
 ```js
 async function query(data) {
 	const response = await fetch(
-		"https://api-inference.huggingface.co/models/<REPO_ID>",
+		"https://api-inference.huggingface.co/models/google/tapas-base-finetuned-wtq",
 		{
 			headers: {
 				Authorization: "Bearer hf_***"

docs/api-inference/tasks/text-classification.md

@@ -43,7 +43,6 @@ curl https://api-inference.huggingface.co/models/distilbert/distilbert-base-unca
 	-d '{"inputs": "I like you. I love you"}' \
 	-H 'Content-Type: application/json' \
 	-H "Authorization: Bearer hf_***"
-
 ```
 </curl>
 

docs/api-inference/tasks/text-generation.md

@@ -42,55 +42,50 @@ This is only a subset of the supported models. Find the model that suits you bes
 
 <curl>
 ```bash
-curl https://api-inference.huggingface.co/models/google/gemma-2-2b-it \
-	-X POST \
-	-d '{"inputs": "Can you please let us know more details about your "}' \
-	-H 'Content-Type: application/json' \
-	-H "Authorization: Bearer hf_***"
+curl 'https://api-inference.huggingface.co/models/google/gemma-2-2b-it/v1/chat/completions' \
+-H "Authorization: Bearer hf_***" \
+-H 'Content-Type: application/json' \
+-d '{
+	"model": "google/gemma-2-2b-it",
+	"messages": [{"role": "user", "content": "What is the capital of France?"}],
+	"max_tokens": 500,
+	"stream": false
+}'
 
 ```
 </curl>
 
 <python>
 ```py
-import requests
-
-API_URL = "https://api-inference.huggingface.co/models/google/gemma-2-2b-it"
-headers = {"Authorization": "Bearer hf_***"}
-
-def query(payload):
-	response = requests.post(API_URL, headers=headers, json=payload)
-	return response.json()
-
-output = query({
-	"inputs": "Can you please let us know more details about your ",
-})
+from huggingface_hub import InferenceClient
+
+client = InferenceClient(api_key="hf_***")
+
+for message in client.chat_completion(
+	model="google/gemma-2-2b-it",
+	messages=[{"role": "user", "content": "What is the capital of France?"}],
+	max_tokens=500,
+	stream=True,
+):
+    print(message.choices[0].delta.content, end="")
 ```
 
 To use the Python client, see `huggingface_hub`'s [package reference](https://huggingface.co/docs/huggingface_hub/package_reference/inference_client#huggingface_hub.InferenceClient.text_generation).
 </python>
 
 <js>
 ```js
-async function query(data) {
-	const response = await fetch(
-		"https://api-inference.huggingface.co/models/google/gemma-2-2b-it",
-		{
-			headers: {
-				Authorization: "Bearer hf_***"
-				"Content-Type": "application/json",
-			},
-			method: "POST",
-			body: JSON.stringify(data),
-		}
-	);
-	const result = await response.json();
-	return result;
-}
+import { HfInference } from "@huggingface/inference";
 
-query({"inputs": "Can you please let us know more details about your "}).then((response) => {
-	console.log(JSON.stringify(response));
-});
+const inference = new HfInference("hf_***");
+
+for await (const chunk of inference.chatCompletionStream({
+	model: "google/gemma-2-2b-it",
+	messages: [{ role: "user", content: "What is the capital of France?" }],
+	max_tokens: 500,
+})) {
+	process.stdout.write(chunk.choices[0]?.delta?.content || "");
+}
 ```
 
 To use the JavaScript client, see `huggingface.js`'s [package reference](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference#textgeneration).