huggingface · kevinzwang · Sep 3, 2025 · Sep 3, 2025 · Sep 3, 2025 · Sep 4, 2025
diff --git a/docs/hub/_toctree.yml b/docs/hub/_toctree.yml
@@ -175,6 +175,8 @@
     sections:
       - local: datasets-argilla
         title: Argilla
+      - local: datasets-daft
+        title: Daft
       - local: datasets-dask
         title: Dask
       - local: datasets-usage

diff --git a/docs/hub/datasets-adding.md b/docs/hub/datasets-adding.md
@@ -67,7 +67,7 @@ The rich features set in the `huggingface_hub` library allows you to manage repo
 
 ## Using other libraries
 
-Some libraries like [🤗 Datasets](/docs/datasets/index), [Pandas](https://pandas.pydata.org/), [Polars](https://pola.rs), [Dask](https://www.dask.org/) or [DuckDB](https://duckdb.org/) can upload files to the Hub.
+Some libraries like [🤗 Datasets](/docs/datasets/index), [Pandas](https://pandas.pydata.org/), [Polars](https://pola.rs), [Dask](https://www.dask.org/), [DuckDB](https://duckdb.org/), or [Daft](https://daft.ai/) can upload files to the Hub.
 See the list of [Libraries supported by the Datasets Hub](./datasets-libraries) for more information.
 
 ## Using Git

diff --git a/docs/hub/datasets-daft.md b/docs/hub/datasets-daft.md
@@ -0,0 +1,79 @@
+# Daft
+
+[Daft](https://daft.ai/) is a high-performance data engine providing simple and reliable data processing for any modality and scale. Daft has native support for reading from and writing to Hugging Face datasets.
+
+<div class="flex justify-center">
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/daft_hf.png"/>
+</div>
+
+
+## Getting Started
+
+To get started, pip install `daft` with the `huggingface` feature:
+
+```bash
+pip install 'daft[hugggingface]'
+```
+
+## Read
+
+Daft is able to read datasets directly from the Hugging Face Hub using the [`daft.read_huggingface()`](https://docs.daft.ai/en/stable/api/io/#daft.read_huggingface) function or via the `hf://datasets/` protocol.
+
+### Reading an Entire Dataset
+
+Using [`daft.read_huggingface()`](https://docs.daft.ai/en/stable/api/io/#daft.read_huggingface), you can easily load a dataset.
+
+
+```python
+import daft
+
+df = daft.read_huggingface("username/dataset_name")
+```
+
+This will read the entire dataset into a DataFrame.
+
+### Reading Specific Files
+
+Not only can you read entire datasets, but you can also read individual files from a dataset repository. Using a read function that takes in a path (such as [`daft.read_parquet()`](https://docs.daft.ai/en/stable/api/io/#daft.read_parquet), [`daft.read_csv()`](https://docs.daft.ai/en/stable/api/io/#daft.read_csv), or [`daft.read_json()`](https://docs.daft.ai/en/stable/api/io/#daft.read_json)), specify a Hugging Face dataset path via the `hf://datasets/` prefix:
+
+```python
+import daft
+
+# read a specific Parquet file
+df = daft.read_parquet("hf://datasets/username/dataset_name/file_name.parquet")
+
+# or a csv file
+df = daft.read_csv("hf://datasets/username/dataset_name/file_name.csv")
+
+# or a set of Parquet files using a glob pattern
+df = daft.read_parquet("hf://datasets/username/dataset_name/**/*.parquet")
+```
+
+## Write
+
+Daft is able to write Parquet files to a Hugging Face dataset repository using [`daft.DataFrame.write_huggingface`](https://docs.daft.ai/en/stable/api/dataframe/#daft.DataFrame.write_deltalake). Daft supports [Content-Defined Chunking](https://huggingface.co/blog/parquet-cdc) and [Xet](https://huggingface.co/blog/xet-on-the-hub) for faster, deduplicated writes.
+
+Basic usage:
+
+```python
+import daft
+
+df: daft.DataFrame = ...
+
+df.write_huggingface("username/dataset_name")
+```
+
+See the [`DataFrame.write_huggingface`](https://docs.daft.ai/en/stable/api/dataframe/#daft.DataFrame.write_deltalake) API page for more info.
+
+## Authentication
+
+The `token` parameter in [`daft.io.HuggingFaceConfig`](https://docs.daft.ai/en/stable/api/config/#daft.io.HuggingFaceConfig) can be used to specify a Hugging Face access token for requests that require authentication (e.g. reading private dataset repositories or writing to a dataset repository).
+
+Example of loading a dataset with a specified token:
+
+```python
+from daft.io import IOConfig, HuggingFaceConfig
+
+io_config = IOConfig(hf=HuggingFaceConfig(token="your_token"))
+df = daft.read_parquet("hf://datasets/username/dataset_name", io_config=io_config)
+```
diff --git a/docs/hub/datasets-libraries.md b/docs/hub/datasets-libraries.md
@@ -9,6 +9,7 @@ The table below summarizes the supported libraries and their level of integratio
 | Library                             | Description                                                                                                                    | Download from Hub | Push to Hub |
 | ----------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ | ----------------- | ----------- |
 | [Argilla](./datasets-argilla)       | Collaboration tool for AI engineers and domain experts that value high quality data.                                           | ✅                | ✅          |
+| [Daft](./datasets-daft)             | Data engine for large scale, multimodal data processing with a Python-native interface.                                        | ✅                | ✅          |
 | [Dask](./datasets-dask)             | Parallel and distributed computing library that scales the existing Python and PyData ecosystem.                               | ✅                | ✅          |
 | [Datasets](./datasets-usage)        | 🤗 Datasets is a library for accessing and sharing datasets for Audio, Computer Vision, and Natural Language Processing (NLP). | ✅                | ✅          |
 | [Distilabel](./datasets-distilabel) | The framework for synthetic data generation and AI feedback.                                                                   | ✅                | ✅          |
@@ -87,7 +88,7 @@ Examples of this kind of integration:
 
 #### Rely on an existing libraries integration with the Hub
 
-Polars, Pandas, Dask, Spark and DuckDB all can write to a Hugging Face Hub repository. See [datasets libraries](https://huggingface.co/docs/hub/datasets-libraries) for more details.
+Polars, Pandas, Dask, Spark, DuckDB, and Daft can all write to a Hugging Face Hub repository. See [datasets libraries](https://huggingface.co/docs/hub/datasets-libraries) for more details.
 
 If you are already using one of these libraries in your code, adding the ability to push to the Hub is straightforward. For example, if you have a synthetic data generation library that can return a Pandas DataFrame, here is the code you would need to write to the Hub:
 

diff --git a/docs/inference-providers/_toctree.yml b/docs/inference-providers/_toctree.yml
@@ -6,42 +6,9 @@
     title: Pricing and Billing
   - local: hub-integration
     title: Hub integration
-  - local: register-as-a-provider
-    title: Register as an Inference Provider
   - local: security
     title: Security
 
-- title: Providers
-  sections:
-  - local: providers/cerebras
-    title: Cerebras
-  - local: providers/cohere
-    title: Cohere
-  - local: providers/fal-ai
-    title: Fal AI
-  - local: providers/featherless-ai
-    title: Featherless AI
-  - local: providers/fireworks-ai
-    title: Fireworks
-  - local: providers/groq
-    title: Groq
-  - local: providers/hyperbolic
-    title: Hyperbolic
-  - local: providers/hf-inference
-    title: HF Inference
-  - local: providers/nebius
-    title: Nebius
-  - local: providers/novita
-    title: Novita
-  - local: providers/nscale
-    title: Nscale
-  - local: providers/replicate
-    title: Replicate
-  - local: providers/sambanova
-    title: SambaNova
-  - local: providers/together
-    title: Together
-
 - title: Guides
   sections:
   - local: guides/first-api-call
@@ -57,25 +24,19 @@
   - local: guides/image-editor
     title: Build an Image Editor
 
-
-- title: API Reference
+- local: tasks/index
+  title: Inference Tasks
   sections:
-  - local: tasks/index
-    title: Index
-  - local: hub-api
-    title: Hub API
-  - title: Popular Tasks
-    sections:
-    - local: tasks/chat-completion
-      title: Chat Completion
-    - local: tasks/feature-extraction
-      title: Feature Extraction
-    - local: tasks/text-to-image
-      title: Text to Image
-    - local: tasks/text-to-video
-      title: Text to Video
+  - local: tasks/chat-completion
+    title: Chat Completion
+  - local: tasks/feature-extraction
+    title: Feature Extraction
+  - local: tasks/text-to-image
+    title: Text to Image
+  - local: tasks/text-to-video
+    title: Text to Video
   - title: Other Tasks
-    isExpanded: false
+    isExpanded: False
     sections:
     - local: tasks/audio-classification
       title: Audio Classification
@@ -108,4 +69,41 @@
     - local: tasks/translation
       title: Translation
     - local: tasks/zero-shot-classification
-      title: Zero Shot Classification
+      title: Zero Shot Classification
+
+- title: Providers
+  sections:
+  - local: providers/cerebras
+    title: Cerebras
+  - local: providers/cohere
+    title: Cohere
+  - local: providers/fal-ai
+    title: Fal AI
+  - local: providers/featherless-ai
+    title: Featherless AI
+  - local: providers/fireworks-ai
+    title: Fireworks
+  - local: providers/groq
+    title: Groq
+  - local: providers/hyperbolic
+    title: Hyperbolic
+  - local: providers/hf-inference
+    title: HF Inference
+  - local: providers/nebius
+    title: Nebius
+  - local: providers/novita
+    title: Novita
+  - local: providers/nscale
+    title: Nscale
+  - local: providers/replicate
+    title: Replicate
+  - local: providers/sambanova
+    title: SambaNova
+  - local: providers/together
+    title: Together
+
+- local: hub-api
+  title: Hub API
+
+- local: register-as-a-provider
+  title: Register as an Inference Provider
diff --git a/docs/inference-providers/providers/featherless-ai.md b/docs/inference-providers/providers/featherless-ai.md
@@ -52,7 +52,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"featherless-ai":{"modelId":"moonshotai/Kimi-K2-Instruct","providerModelId":"moonshotai/Kimi-K2-Instruct"} } }
+    providersMapping={ {"featherless-ai":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct"} } }
 conversational />
 
 
@@ -72,6 +72,6 @@ Find out more about Text Generation [here](../tasks/text_generation).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"featherless-ai":{"modelId":"moonshotai/Kimi-K2-Instruct","providerModelId":"moonshotai/Kimi-K2-Instruct"} } }
+    providersMapping={ {"featherless-ai":{"modelId":"meta-llama/Llama-3.1-8B-Instruct","providerModelId":"meta-llama/Meta-Llama-3.1-8B-Instruct"} } }
 />
 
diff --git a/docs/inference-providers/providers/hf-inference.md b/docs/inference-providers/providers/hf-inference.md
@@ -57,16 +57,6 @@ Find out more about Automatic Speech Recognition [here](../tasks/automatic_speec
 />
 
 
-### Chat Completion (LLM)
-
-Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
-
-<InferenceSnippet
-    pipeline=text-generation
-    providersMapping={ {"hf-inference":{"modelId":"HuggingFaceTB/SmolLM3-3B","providerModelId":"HuggingFaceTB/SmolLM3-3B"} } }
-conversational />
-
-
 ### Feature Extraction
 
 Find out more about Feature Extraction [here](../tasks/feature_extraction).
@@ -93,7 +83,7 @@ Find out more about Image Classification [here](../tasks/image_classification).
 
 <InferenceSnippet
     pipeline=image-classification
-    providersMapping={ {"hf-inference":{"modelId":"Falconsai/nsfw_image_detection","providerModelId":"Falconsai/nsfw_image_detection"} } }
+    providersMapping={ {"hf-inference":{"modelId":"dima806/fairface_age_image_detection","providerModelId":"dima806/fairface_age_image_detection"} } }
 />
 
 
@@ -103,7 +93,7 @@ Find out more about Image Segmentation [here](../tasks/image_segmentation).
 
 <InferenceSnippet
     pipeline=image-segmentation
-    providersMapping={ {"hf-inference":{"modelId":"mattmdjaga/segformer_b2_clothes","providerModelId":"mattmdjaga/segformer_b2_clothes"} } }
+    providersMapping={ {"hf-inference":{"modelId":"facebook/mask2former-swin-small-ade-semantic","providerModelId":"facebook/mask2former-swin-small-ade-semantic"} } }
 />
 
 
@@ -153,17 +143,7 @@ Find out more about Text Classification [here](../tasks/text_classification).
 
 <InferenceSnippet
     pipeline=text-classification
-    providersMapping={ {"hf-inference":{"modelId":"ProsusAI/finbert","providerModelId":"ProsusAI/finbert"} } }
-/>
-
-
-### Text Generation
-
-Find out more about Text Generation [here](../tasks/text_generation).
-
-<InferenceSnippet
-    pipeline=text-generation
-    providersMapping={ {"hf-inference":{"modelId":"HuggingFaceTB/SmolLM3-3B","providerModelId":"HuggingFaceTB/SmolLM3-3B"} } }
+    providersMapping={ {"hf-inference":{"modelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english","providerModelId":"distilbert/distilbert-base-uncased-finetuned-sst-2-english"} } }
 />
 
 
@@ -183,7 +163,7 @@ Find out more about Token Classification [here](../tasks/token_classification).
 
 <InferenceSnippet
     pipeline=token-classification
-    providersMapping={ {"hf-inference":{"modelId":"iiiorg/piiranha-v1-detect-personal-information","providerModelId":"iiiorg/piiranha-v1-detect-personal-information"} } }
+    providersMapping={ {"hf-inference":{"modelId":"microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank","providerModelId":"microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank"} } }
 />
 
 
@@ -203,6 +183,6 @@ Find out more about Zero Shot Classification [here](../tasks/zero_shot_classific
 
 <InferenceSnippet
     pipeline=zero-shot-classification
-    providersMapping={ {"hf-inference":{"modelId":"facebook/bart-large-mnli","providerModelId":"facebook/bart-large-mnli"} } }
+    providersMapping={ {"hf-inference":{"modelId":"joeddav/xlm-roberta-large-xnli","providerModelId":"joeddav/xlm-roberta-large-xnli"} } }
 />
 
diff --git a/docs/inference-providers/providers/nebius.md b/docs/inference-providers/providers/nebius.md
@@ -50,7 +50,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"nebius":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"} } }
+    providersMapping={ {"nebius":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"} } }
 conversational />
 
 
@@ -80,7 +80,7 @@ Find out more about Text Generation [here](../tasks/text_generation).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"nebius":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"} } }
+    providersMapping={ {"nebius":{"modelId":"openai/gpt-oss-20b","providerModelId":"openai/gpt-oss-20b"} } }
 />
 
 

diff --git a/docs/inference-providers/providers/replicate.md b/docs/inference-providers/providers/replicate.md
@@ -70,6 +70,6 @@ Find out more about Text To Video [here](../tasks/text_to_video).
 
 <InferenceSnippet
     pipeline=text-to-video
-    providersMapping={ {"replicate":{"modelId":"Wan-AI/Wan2.2-TI2V-5B","providerModelId":"wan-video/wan-2.2-5b-fast"} } }
+    providersMapping={ {"replicate":{"modelId":"Wan-AI/Wan2.2-T2V-A14B","providerModelId":"wan-video/wan-2.2-t2v-fast"} } }
 />
 
diff --git a/docs/inference-providers/providers/together.md b/docs/inference-providers/providers/together.md
@@ -50,7 +50,7 @@ Find out more about Chat Completion (LLM) [here](../tasks/chat-completion).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"together":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"} } }
+    providersMapping={ {"together":{"modelId":"openai/gpt-oss-20b","providerModelId":"OpenAI/gpt-oss-20B"} } }
 conversational />
 
 
@@ -70,7 +70,7 @@ Find out more about Text Generation [here](../tasks/text_generation).
 
 <InferenceSnippet
     pipeline=text-generation
-    providersMapping={ {"together":{"modelId":"openai/gpt-oss-120b","providerModelId":"openai/gpt-oss-120b"} } }
+    providersMapping={ {"together":{"modelId":"openai/gpt-oss-20b","providerModelId":"OpenAI/gpt-oss-20B"} } }
 />