Files
langchain/libs/partners/huggingface
langchain-oss-model-profiles[bot]andmdrxy aac7904ff4 chore(model-profiles): refresh model profile data (#40198)
Automated refresh of model profile data for all in-monorepo partner
integrations via `langchain-profiles refresh`.

🤖 Generated by the [`refresh_model_profiles`
workflow](https://github.com/langchain-ai/langchain/blob/master/.github/workflows/refresh_model_profiles.yml).

## Summary of changes

**3 added · 0 removed · 9 changed** across 3 provider(s).

<details>
<summary>fireworks-ai</summary>

**✏️ 2 changed**
- `accounts/fireworks/models/glm-5p3`: last updated `2026-08-28` →
`2026-09-04`
- `accounts/fireworks/models/glm-5p3-flash`: last updated `2026-08-26` →
`2026-09-04`

</details>

<details>
<summary>huggingface</summary>

**➕ 1 added**
- `deepseek-ai/DeepSeek-V4-Flash-Vision-Exp` — 1,048,576 ctx, 384,000
out, text+image in, reasoning, tools

</details>

<details>
<summary>openrouter</summary>

**➕ 2 added**
- `inclusionai/ling-3.0-flash-fin` — 262,144 ctx, 235,929 out,
reasoning, tools
- `nvidia/nemotron-3.5-content-safety` — 131,072 ctx, 117,964 out,
text+image in, reasoning

**✏️ 7 changed**
- `deepseek/deepseek-chat`: max output tokens 16,000 → 16,384
- `deepseek/deepseek-chat-v3.1`: max output tokens 32,768 → 144,900
- `nvidia/nemotron-3-ultra-550b-a55b`: max output tokens 182,520 →
32,768
- `qwen/qwen2.5-vl-72b-instruct`: max output tokens 28,800 → 115,200
- `undi95/remm-slerp-l2-13b`: max output tokens 4,096 → 5,529
- `z-ai/glm-5.3`: max output tokens 131,072 → 262,144
- `~z-ai/glm-latest`: max output tokens 943,718 → 235,929

</details>

Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com>
2026-09-04 11:19:24 -04:00
..
2024-05-13 20:53:15 +00:00
2024-05-13 20:53:15 +00:00
2026-06-12 14:54:25 -04:00

langchain-huggingface

PyPI - Version PyPI - License PyPI - Downloads Twitter

Looking for the JS/TS version? Check out LangChain.js.

Quick Install

uv add langchain-huggingface

Note: The base install does not include sentence-transformers or transformers. If you plan to use HuggingFaceEmbeddings or HuggingFacePipeline for local inference, install the [full] extra which includes sentence-transformers>=5.2.0 and transformers>=5.0.0:

uv add "langchain-huggingface[full]"

Migrating from langchain-community? Note that langchain-community accepted sentence-transformers>=2.2.0, but langchain-huggingface[full] requires >=5.2.0. If your project pins an older version, upgrade it:

uv add "sentence-transformers>=5.2.0"

🤔 What is this?

This package contains the LangChain integrations for Hugging Face related classes.

📖 Documentation

For full documentation, see the API reference. For conceptual guides, tutorials, and examples on using these classes, see the LangChain Docs.

📕 Releases & Versioning

See our Releases and Versioning policies.

💁 Contributing

As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.

For detailed information on how to contribute, see the Contributing Guide.

Resources

  • LangChain Academy — comprehensive, free courses on LangChain libraries and products, made by the LangChain team
  • Code of Conduct — community guidelines and standards