This page tracks feature releases and model updates for AI Search Open Platform.
2025
June
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | Speech recognition | Call the speech recognition API to convert speech from videos or audio files into structured text. Supports meeting transcription, video content retrieval, and online customer service. | 2025-06-26 | Speech recognition |
| New | Video snapshot | Call the video snapshot API to extract keyframes from videos. Combine with optical character recognition (OCR), image parsing, or multimodal embedding for deep video content analysis. | 2025-06-26 | Video snapshot |
| Update | ops-qwen3-embedding-0.6b added to text embedding | New multilingual text embedding model from the Qwen3 series. Key specs: 100+ languages supported, 32k max input length, 32–1024 customizable output dimensions, 0.6B parameters. | 2025-06-26 | Text embedding |
| Update | ops-qwen3-reranker-0.6b added to re-rank service | New re-ranking model from the Qwen3 series. Key specs: 100+ languages supported, 32k max input token length (query + document combined), 0.6B parameters. | 2025-06-26 | Re-rank service |
| Update | ops-gme-qwen2-vl-2b-instruct added to multimodal embedding service | New multimodal embedding model trained on the Qwen2-VL multimodal large language model (MLLM). Handles text-only, image-only, and mixed text-image inputs. | 2025-06-26 | Multimodal embedding |
| New | Multimodal embedding | Multimodal embedding service trained on the Qwen2-VL MLLM. Supports single-modal and multimodal combination inputs, including text, images, and mixed data. | 2025-06-04 | Multimodal embedding |
April
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| Update | Qwen3-235B-A22B added to LLM service | New large language model (LLM) from the Qwen3 series. Key specs: 100+ languages and dialects supported, with improvements in reasoning, instruction following, and agent capability. | 2025-04-29 | Content generation |
March
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | Web search | Call the web search API independently or use it within LLM-based conversational search workflows. | 2025-03-20 | Internet search |
| Update | QwQ deep thinking model | Reasoning model trained on Qwen2.5-32B with reinforcement learning. Performance on math and coding benchmarks (AIME 24/25, LiveCodeBench) and general benchmarks (IFEval, LiveBench) reaches the level of the DeepSeek-R1 full version. | 2025-03-20 | Content generation |
| Update | Model deployment | ModelScope is now supported as a model source. Newly supported model types: multimodal embedding models and re-ranking models. | 2025-03-13 | Model deployment |
| New | Service development | AI Search Open Platform is now integrated with Data Science Workshop (DSW) of Platform for AI (PAI). Use Notebook in DSW to develop and run services. | 2025-03-13 | Service development |
February
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | DeepSeek models | All DeepSeek models are now available, including DeepSeek R1/V3 and 7B/14B distilled models. Call them using the OpenAI-compatible API. | 2025-02-14 | Model list |
January
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | Model deployment | Deploy models independently in AI Search Open Platform for inference services with higher concurrency and lower latency. | 2025-01-07 | Model deployment |
2024
October
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | Vector dimensionality reduction service | Train custom vector dimensionality reduction models using your own vector data. | 2024-10-23 | Vector dimensionality reduction service |
September
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | Re-ranking model | Self-developed re-ranking model trained on multi-industry datasets. Supports multiple languages and outperforms open-source bge-rerank series models across 8 retrieval tasks on the Chinese MTEB benchmark. | 2024-09-12 | Re-rank service |
| New | NL2SQL added to the query analysis service | Natural language to SQL (NL2SQL) capability added to the query analysis service. Configure and call the NL2SQL service to convert natural language queries into SQL statements. | 2024-09-12 | Configure the NL2SQL feature and Query analysis |
| New | Multimodal data processing scenario | New scenario added to the scenario center for text and image parsing and embedding. | 2024-09-12 | Parse and embedding multimodal data |
| New | LlamaIndex code architecture added to the RAG scenario | LlamaIndex code architecture added to the scenario center for building retrieval-augmented generation (RAG)-based conversational search applications. | 2024-09-12 | Build a RAG-based conversational search application |
August
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| Optimized | OCR optimization in image parsing | OCR performance in image parsing improved by approximately 40%. | 2024-08 | Image content extraction |
July
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | Evaluation management | Evaluate the effectiveness of your RAG pipeline. Upload an evaluation dataset and get LLM-based evaluation results. | 2024-07-08 | Manage evaluation tasks |
| New | Data upload in the experience center | Upload your own data to the experience center to test services with real content. | 2024-07-08 | Experience center |
| New | OpenAI SDK compatibility | Call AI Search Open Platform services using the OpenAI SDK. The platform is compatible with OpenAI interfaces. | 2024-07-08 | Supported service list |
| New | LangChain code architecture added to the RAG scenario | LangChain code architecture added to the scenario center for building RAG-based conversational search applications. | 2024-07-08 | Build a RAG-based conversational search application |
| New | Query analysis service | Analyze queries using LLMs and NLP to understand user intent, generate similar questions, and convert natural language to SQL. Improves conversational search performance in RAG scenarios. | 2024-07-08 | Query analysis |
| New | Image parsing service | Parse image content using multimodal LLMs, including text extracted from images, for use in image retrieval and conversational search. | 2024-07-08 | Image content extraction |
| New | Query analysis service experience | Query analysis service added to the experience center. Test intent detection and similar query generation based on historical messages. | 2024-07-30 | Experience center |
| New | Image parsing in RAG scenarios | Image parsing in documents is now supported in RAG scenarios. Combined with the query analysis service, run conversational search on rewritten queries. | 2024-07-30 | Build a RAG-based conversational search application |
| New | VPC access regions | VPC access to services now supported in the China (Shanghai), China (Hangzhou), China (Shenzhen), China (Beijing), China (Qingdao), and China (Zhangjiakou) regions. | 2024-07-30 | Query service endpoint |
June
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | RAG-based conversational search application | End-to-end RAG solution for knowledge base conversational search, covering data preprocessing, data retrieval, and output generation. | 2024-06-18 | Build a RAG-based conversational search application |
May
| Type | Feature | Description | Release date | Reference |
|---|---|---|---|---|
| New | LLM | LLM service added, including Qwen models and fine-tuned RAG-specific LLMs. | 2024-05-21 | Service overview |
| New | Re-ranking service | Re-ranking service added for general document scoring. Ranks documents by query-document relevance in descending order and returns scores. | 2024-05-21 | Re-rank service |
| New | Sparse text embedding service | Sparse text embedding service added. Converts text into sparse vectors. | 2024-05-21 | Sparse text embedding |
| New | Text embedding service | Text embedding service added. Converts text into dense vectors. | 2024-05-21 | Text embedding |
| New | Document chunking service | Document chunking service added. Split HTML, Markdown, and TXT documents by paragraph structure, semantic meaning, or custom rules. Extract code, images, and tables from rich-text content. | 2024-05-21 | Document chunking |
| New | Document parsing service | Document parsing service added. Extract logical structure and content from unstructured documents, including titles, paragraphs, text, tables, and images, in structured output format. | 2024-05-21 | Document content parsing |
| New | Service experience | Service experience added to the console. Try text parsing, chunking, embedding, re-ranking, LLM, and other services directly in the browser. | 2024-05-21 | Experience center |