Apply feedback for "new_api_docs"

docs/api-inference/getting-started.md

@@ -6,19 +6,23 @@ We'll do a minimal example using a [sentiment classification model](https://hugg
 
 ## Getting a Token
 
-Using the Serverless Inference API requires passing a user token in the request headers. You can get a token by signing up on the Hugging Face website and then going to the [tokens page](https://huggingface.co/settings/tokens). We recommend creating a `Fine-grained` token with the scope to `Make calls to the serverless Inference API`.
+Using the Serverless Inference API requires passing a user token in the request headers. You can get a token by signing up on the Hugging Face website and then going to the [tokens page](https://huggingface.co/settings/tokens/new?globalPermissions=inference.serverless.write&tokenType=fineGrained). We recommend creating a `Fine-grained` token with the scope to `Make calls to the serverless Inference API`.
 
 TODO: add screenshot
 For more details about user tokens, check out [this guide](https://huggingface.co/docs/hub/en/security-tokens).
 
 ## cURL
 
 ```bash
-curl https://api-inference.huggingface.co/models/cardiffnlp/twitter-roberta-base-sentiment-latest \
-    -X POST \
-    -d '{"inputs": "Today is a nice day"}' \
-    -H "Authorization: Bearer hf_***" \
-    -H "Content-Type: application/json"
+curl 'https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3.1-8B-Instruct/v1/chat/completions' \
+-H "Authorization: Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
+-H 'Content-Type: application/json' \
+-d '{
+    "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "max_tokens": 500,
+    "stream": false
+}'
 ```
 
 ## Python
@@ -28,21 +32,35 @@ You can use the `requests` library to make a request to the Inference API.
 ```python
 import requests
 
-API_URL = "https://api-inference.huggingface.co/models/cardiffnlp/twitter-roberta-base-sentiment-latest"
-headers = {"Authorization": "Bearer hf_***"}
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3.1-8B-Instruct/v1/chat/completions"
+headers = {"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
+payload = {
+    "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    "messages": [{"role": "user", "content": "What is the capital of France?"}],
+    "max_tokens": 500,
+    "stream": False
+}
 
-payload = {"inputs": "Today is a nice day"}
 response = requests.post(API_URL, headers=headers, json=payload)
 response.json()
 ```
 
-Hugging Face also provides a [`InferenceClient`](https://huggingface.co/docs/huggingface_hub/guides/inference) that handles inference, caching, async, and more. Make sure to install it with `pip install huggingface_hub` first
+Hugging Face also provides a [`InferenceClient`](https://huggingface.co/docs/huggingface_hub/guides/inference) that handles inference for you. Make sure to install it with `pip install huggingface_hub` first.
 
 ```python
 from huggingface_hub import InferenceClient
 
-client = InferenceClient(model="cardiffnlp/twitter-roberta-base-sentiment-latest", token="hf_***")
-client.text_classification("Today is a nice day")
+client = InferenceClient(
+    "meta-llama/Meta-Llama-3.1-8B-Instruct",
+    token="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+)
+
+for message in client.chat_completion(
+	messages=[{"role": "user", "content": "What is the capital of France?"}],
+	max_tokens=500,
+	stream=True,
+):
+    print(message.choices[0].delta.content, end="")
 ```
 
 ## JavaScript
@@ -52,11 +70,11 @@ import fetch from "node-fetch";
 
 async function query(data) {
     const response = await fetch(
-        "https://api-inference.huggingface.co/models/MODEL_ID",
+        "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3.1-8B-Instruct/v1/chat/completions",
         {
             method: "POST",
             headers: {
-                Authorization: `Bearer cardiffnlp/twitter-roberta-base-sentiment-latest`,
+                Authorization: `Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx`,
                 "Content-Type": "application/json",
             },
             body: JSON.stringify(data),
@@ -67,12 +85,31 @@ async function query(data) {
 }
 
 query({
-    inputs: "Today is a nice day"
+	"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+	"messages": [{"role": "user", "content": "What is the capital of France?"}],
+	"max_tokens": 500,
+	"stream": false
 }).then((response) => {
     console.log(JSON.stringify(response, null, 2));
 });
 ```
 
+Hugging Face also provides a [`HfInference`](https://huggingface.co/docs/huggingface.js/inference/classes/HfInference) client that handles inference. Make sure to install it with `npm install @huggingface/inference` first.
+
+```js
+import { HfInference } from "@huggingface/inference";
+
+const inference = new HfInference("hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx");
+
+for await (const chunk of inference.chatCompletionStream({
+	model: "meta-llama/Meta-Llama-3.1-8B-Instruct",
+	messages: [{ role: "user", content: "What is the capital of France?" }],
+	max_tokens: 500,
+})) {
+	process.stdout.write(chunk.choices[0]?.delta?.content || "");
+}
+```
+
 ## Next Steps
 
 Now that you know the basics, you can explore the [API Reference](./parameters.md) to learn more about task-specific settings and parameters. 

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

@@ -27,37 +27,6 @@ For more details about the `audio-classification` task, check out its [dedicated
 
 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=audio-classification&sort=trending).
 
-### API specification
-
-#### Request
-
-| Payload |  |  |
-| :--- | :--- | :--- |
-| **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 Audio Classification |
-| **        function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. |
-| **        top_k** | _integer_ | When specified, limits the output to the top K most probable classes. |
-
-
-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
-
-| Body |  |
-| :--- | :--- | :--- |
-| **(array)** | _object[]_ | Output is an array of objects. |
-| **        label** | _string_ | The predicted class label. |
-| **        score** | _number_ | The corresponding probability. |
-
-
 ### Using the API
 
 
@@ -122,3 +91,34 @@ To use the JavaScript client, see `huggingface.js`'s [package reference](https:/
 </inferencesnippet>
 
 
+
+### API specification
+
+#### Request
+
+| Payload |  |  |
+| :--- | :--- | :--- |
+| **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 Audio Classification |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;function_to_apply** | _enum_ | Possible values: sigmoid, softmax, none. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;top_k** | _integer_ | When specified, limits the output to the top K most probable classes. |
+
+
+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
+
+| Body |  |
+| :--- | :--- | :--- |
+| **(array)** | _object[]_ | Output is an array of objects. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;label** | _string_ | The predicted class label. |
+| **&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;score** | _number_ | The corresponding probability. |
+