Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 34 additions & 2 deletions cicd/massive-redirect/en.json
Original file line number Diff line number Diff line change
Expand Up @@ -1366,10 +1366,42 @@
,
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/e5-mistral-7b-instruct/",
"moved": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/"
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/gemma-3/",
"moved": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/"
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/",
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/",
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/baai-bge-reranker-v2-m3/",
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/baai-bge-reranker-v2-m3/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/e5-mistral-7b-instruct/",
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/e5-mistral-7b-instruct/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/internvl3/",
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/internvl3/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/mistral-3-small/",
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/mistral-3-small/"
},
{
"from": "https://www.azion.com/en/documentation/products/ai/edge-ai/models/qwen-2-5-vl-3b/",
"moved": "https://www.azion.com/en/documentation/products/ai/ai-inference/models/qwen-2-5-vl-3b/"
},
{
"from": "https://www.azion.com/en/documentation/products/guides/edge-ai-starter-kit/",
"moved": "https://www.azion.com/en/documentation/products/guides/ai-inference-starter-kit/"
}
]
35 changes: 31 additions & 4 deletions cicd/massive-redirect/pt-br.json
Original file line number Diff line number Diff line change
Expand Up @@ -1380,11 +1380,38 @@
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/e5-mistral-7b-instruct/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/"
}
,
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/gemma-3/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/"
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/baai-bge-reranker-v2-m3/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/baai-bge-reranker-v2-m3/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/e5-mistral-7b-instruct/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/e5-mistral-7b-instruct/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/internvl3/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/internvl3/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/mistral-3-small/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/mistral-3-small/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/modelos/qwen-2-5-vl-3b/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/modelos/qwen-2-5-vl-3b/"
},
{
"from": "https://www.azion.com/pt-br/documentacao/produtos/ai/edge-ai/",
"moved": "https://www.azion.com/pt-br/documentacao/produtos/ai/ai-inference/"
}
]
2 changes: 1 addition & 1 deletion src/content/docs/en/pages/guides/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,7 @@ permalink: /documentation/products/guides/
- [How to deploy the Docusaurus TypeScript Boilerplate](/en/documentation/products/guides/docusaurus-typescript-boilerplate/)
- [How to deploy the Docusaurus with Material UI template](/en/documentation/products/guides/docusaurus-material-ui-template/)
- [How to deploy the Dynamic and Static File Optimization template](/en/documentation/products/guides/dynamic-and-static-file-optimization-template/)
- [How to deploy the Edge AI Starter Kit template](/en/documentation/products/guides/edge-ai-starter-kit/)
- [How to deploy the AI Inference Starter Kit template](/en/documentation/products/guides/ai-inference-starter-kit/)
- [How to deploy the Edge Application Proxy template](/en/documentation/products/guides/edge-application-proxy-template/)
- [How to deploy the Edge Function Starter Kit template](/en/documentation/products/guides/edge-function-starter-kit/)
- [How to deploy the EdgeSQL Starter Kit template](/en/documentation/products/guides/edgesql-starter-kit/)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ The integrations are organized into various categories, making it easy to explor
- **Security**: authenticate users, validate input data, route requests, define rate limiting, and scan and filter content to protect your applications from malicious attacks.
- **Performance**: reduce the load on your servers, minimize network latency, and accelerate content delivery, providing an improved experience for users.
- **Database**: manage your databases in a smooth way and generate dynamic content as demanded, such as personalized recommendations or geolocalized messages, based on user preferences or real-time data.
- **Edge AI**: implement facial recognition and ID matching tools, and accelerate and automate processes with state-of-the-art integrations.
- **AI Inference**: implement facial recognition and ID matching tools, and accelerate and automate processes with state-of-the-art integrations.

---

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -297,11 +297,11 @@ This template helps you deploy a Docusaurus website integrated with Material UI
icon-pos="left"
/>

#### Edge AI Starter Kit
#### AI Inference Starter Kit

The **Edge AI Starter Kit** template helps you create an edge AI-based application without origin dependencies.
The **AI Inference Starter Kit** template helps you create an edge AI-based application without origin dependencies.

<LinkButton link="/en/documentation/products/guides/edge-ai-starter-kit/" label="Go to the Edge AI Starter Kit guide" severity="secondary" />
<LinkButton link="/en/documentation/products/guides/edge-ai-starter-kit/" label="Go to the AI Inference Starter Kit guide" severity="secondary" />

<LinkButton
label="Deploy"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
title: Qwen3 30B A3B Instruct 2507 FP8
description: >-
Qwen3-30B-A3B-Instruct-2507-FP8 is an instruction-tuned 30B-parameter FP8 causal language model for long-context (256K) text generation and reasoning, supporting chat/QA, summarization, multilingual tasks, math/science problem solving, coding, and tool-augmented workflows.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing, qwen'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing, qwen'
namespace: docs_edge_ai_models_qwen_3_30ba3b
permalink: /documentation/products/ai/ai-inference/models/qwen3-30ba3b/
---
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
title: BAAI/bge-reranker-v2-m3
description: >-
BAAI/bge-reranker-v2-m3 is a lightweight reranker model with strong multilingual capabilities.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing'
namespace: docs_edge_ai_models_baai_bge_reranker_v2_m3
permalink: /documentation/products/ai/edge-ai/models/baai-bge-reranker-v2-m3/
permalink: /documentation/products/ai/ai-inference/models/baai-bge-reranker-v2-m3/
---

**BAAI/bge-reranker-v2-m3** is a lightweight reranker model with strong multilingual capabilities. It's easy to deploy and offers fast inference.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
title: InternVL3
description: >-
InternVL3 is an advanced multimodal large language model with capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing'
namespace: docs_edge_ai_models_internvl3
permalink: /documentation/products/ai/edge-ai/models/internvl3/
permalink: /documentation/products/ai/ai-inference/models/internvl3/
---

**InternVL3** is an advanced multimodal large language model (MLLM) with capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
title: Mistral 3 Small (24B AWQ)
description: >-
Mistral 3 Small provides a range of capabilities, including text generation, image analysis, embeddings, and more.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing, mistral'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing, mistral'
namespace: docs_edge_ai_models_mistral_3_small
permalink: /documentation/products/ai/edge-ai/models/mistral-3-small/
permalink: /documentation/products/ai/ai-inference/models/mistral-3-small/
---

**Mistral 3 Small** is a language model that delivers capabilities comparable to larger models while being compact. It's ideal for conversational agents, function calling, fine-tuning, and local inference with sensitive data.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
title: Nanonets-OCR-s
description: >-
Nanonets-OCR-s is an OCR model that converts document images to structured Markdown, preserving layout (headings, lists, tables) and basic tags. The output is easy to parse and feed into LLM pipelines.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing, qwen'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing, qwen'
namespace: docs_edge_ai_models_nanonets_ocr_s
permalink: /documentation/products/ai/ai-inference/models/nanonets-ocr-s/
---
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
title: Qwen2.5 VL AWQ 3B
description: >-
Qwen2.5 VL AWQ 3B is a vision-language model that supports 3 bilion parameters and offers advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing, qwen'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing, qwen'
namespace: docs_edge_ai_models_qwen_2_5_vl_3b
permalink: /documentation/products/ai/edge-ai/models/qwen-2-5-vl-3b/
permalink: /documentation/products/ai/ai-inference/models/qwen-2-5-vl-3b/
---

**Qwen2.5 VL AWQ 3B** is a vision-language model that offers advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation. It supports 3 bilion parameters.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,9 @@
title: Qwen2.5 VL AWQ 7B
description: >-
Qwen2.5 VL AWQ 7B is a vision-language model that supports 7 billion parameters, offering advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing, qwen'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing, qwen'
namespace: docs_edge_ai_models_qwen_2_5_vl_7b
permalink: /documentation/products/ai/edge-ai/models/qwen-2-5-vl-7b/
permalink: /documentation/products/ai/ai-inference/models/qwen-2-5-vl-7b/
---

**Qwen2.5 VL AWQ 7B** is a vision-language model that supports 7 billion parameters, offering advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
title: Qwen3 Embedding 4b
description: >-
Qwen3 Embedding 4B is a 4B-parameter multilingual embedding model (36 layers, 32K context) that outputs 2560‑dim vectors for text/code retrieval, classification, clustering, and bitext mining. It supports instruction-conditioned embeddings and is optimized for efficient, cross-lingual representation learning.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing, qwen'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing, qwen'
namespace: docs_edge_ai_models_qwen_3_embedding_4b
permalink: /documentation/products/ai/ai-inference/models/qwen3-embedding-4b/
---
Expand Down
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
---
title: Azion Edge AI
title: Azion AI Inference
description: >-
Azion Edge AI empowers you to build and deploy intelligent applications that process data close to where it is generated.
meta_tags: 'edge ai, artificial intelligence, edge computing'
meta_tags: 'ai inference, artificial intelligence, edge computing'
namespace: docs_edge_ai_reference
permalink: /documentation/products/ai/edge-ai/
permalink: /documentation/products/ai/ai-inference/
---

import LinkButton from 'azion-webkit/linkbutton';
Expand All @@ -28,7 +28,7 @@ Edge AI gives you access to:

Access our catalog of open-source AI models that you can run directly on Azion Runtime. These models are optimized for edge deployment with minimal resource requirements.

<LinkButton link="/en/documentation/products/ai/edge-ai/models/" label="See Available Models" severity="secondary" />
<LinkButton link="/en/documentation/products/ai/ai-inference/models/" label="See Available Models" severity="secondary" />

### Model customization

Expand Down
Original file line number Diff line number Diff line change
@@ -1,49 +1,49 @@
---
title: Azion Edge AI Models
title: Azion AI Inference Models
description: >-
Edge AI offers a diverse range of edge-optimized models for various AI domains, ensuring efficient deployment and performance.
meta_tags: 'edge ai, ai models, artificial intelligence, edge computing'
meta_tags: 'ai inference, ai models, artificial intelligence, edge computing'
namespace: docs_edge_ai_models
permalink: /documentation/products/ai/edge-ai/models/
permalink: /documentation/products/ai/ai-inference/models/
---

import LinkButton from 'azion-webkit/linkbutton';

Azion's edge-optimized models span multiple AI domains including text generation, image analysis, embeddings, and more. Each model is designed to balance performance and resource efficiency for edge deployment.

This page provides a list of models available for use with **Edge AI**. To learn more about it, visit the [Edge AI Reference](/en/documentation/products/ai/edge-ai/).
This page provides a list of models available for use with **Edge AI**. To learn more about it, visit the [Edge AI Reference](/en/documentation/products/ai/ai-inference/).

## Available Models

### Mistral 3 Small (24B AWQ)

This is a language model that delivers capabilities comparable to larger models while being compact. It is ideal for conversational agents, function calling, fine-tuning, and local inference with sensitive data.

<LinkButton link="/en/documentation/products/ai/edge-ai/models/mistral-3-small/" label="View details" severity="secondary" />
<LinkButton link="/en/documentation/products/ai/ai-inference/models/mistral-3-small/" label="View details" severity="secondary" />

### BAAI/bge-reranker-v2-m3

A lightweight reranker model with strong multilingual capabilities. It offers multilingual support and it's easy to deploy, with fast inference.

<LinkButton link="/en/documentation/products/ai/edge-ai/models/baai-bge-reranker-v2-m3/" label="View details" severity="secondary" />
<LinkButton link="/en/documentation/products/ai/ai-inference/models/baai-bge-reranker-v2-m3/" label="View details" severity="secondary" />

### InternVL3

InternVL3 is an advanced multimodal large language model with capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.

<LinkButton link="/en/documentation/products/ai/edge-ai/models/internvl3/" label="View details" severity="secondary" />
<LinkButton link="/en/documentation/products/ai/ai-inference/models/internvl3/" label="View details" severity="secondary" />

### Qwen2.5 VL AWQ 3B

A Vision Language Model (VLM) that offers advanced capabilities such as visual analysis, agentic reasoning, long video comprehension, visual localization, and structured output generation.

<LinkButton link="/en/documentation/products/ai/edge-ai/models/qwen-2-5-vl-3b/" label="View details" severity="secondary" />
<LinkButton link="/en/documentation/products/ai/ai-inference/models/qwen-2-5-vl-3b/" label="View details" severity="secondary" />

### Qwen2.5 VL AWQ 7B

An instruction-tuned 30B-parameter FP8 causal language model for long-context (256K) text generation and reasoning, supporting chat/QA, summarization, multilingual tasks, math/science problem solving, coding, and tool-augmented workflows.

<LinkButton link="/en/documentation/products/ai/edge-ai/models/qwen-2-5-vl-7b/" label="View details" severity="secondary" />
<LinkButton link="/en/documentation/products/ai/ai-inference/models/qwen-2-5-vl-7b/" label="View details" severity="secondary" />

### Qwen3 30B A3B Instruct 2507 FP8

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -59,9 +59,9 @@ Edge Functions provides support for advanced AI workflows, enabling you to:
- Leverage native [Edge SQL](/en/documentation/products/store/edge-sql/) integration for RAG implementations and vector storage, along with MCP Servers that enable agent-to-agent collaboration using Google's Agent2Agent (A2A) protocol.
- Access state-of-the-art models like Mistral, Florence, Qwen, and others, that follow OpenAI's API standard, all while reducing complexity with a fully integrated AI infrastructure running at the edge of the network.

Azion's **Edge AI** allows you to run AI models on Azion Runtime, and can be used together with Edge Functions to create complex AI-powered applications.
Azion's **AI Inference** allows you to run AI models on Azion Runtime, and can be used together with Edge Functions to create complex AI-powered applications.

<LinkButton link="/en/documentation/products/ai/edge-ai/" label="Learn more about Edge AI" severity="secondary" target="_blank" />
<LinkButton link="/en/documentation/products/ai/ai-inference/" label="Learn more about AI Inference" severity="secondary" target="_blank" />

---

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ curl --location 'https://api.azion.com/v4/edge_sql/databases/{id_database}/query

[Vector Search](/en/documentation/products/store/edge-sql/vector-search/) is an **Azion Edge SQL** feature that enables customers to implement semantic search engines. While traditional search models aim to find exact matches, such as keyword matches, vector search models use specialized algorithms to identify similar items based on their mathematical representations, or vector embeddings.

This feature natively integrates with [Edge AI](/en/documentation/products/ai/edge-ai/) to power RAG implementations without additional infrastructure, combining SQL and vector capabilities in a single database. The system supports **LangChain Vector Store** integration for document storage and **LangChain Retriever** for advanced hybrid search combining vector and full-text search capabilities.
This feature natively integrates with [AI Inference](/en/documentation/products/ai/ai-inference/) to power RAG implementations without additional infrastructure, combining SQL and vector capabilities in a single database. The system supports **LangChain Vector Store** integration for document storage and **LangChain Retriever** for advanced hybrid search combining vector and full-text search capabilities.

---

Expand Down
Loading