DeepSeek officially announced that the API has been upgraded to the million-token context version, consistent with the App and web version. Previously, it was only 128k tokens. This update significantly improves the coherence of conversations and the richness of information. At the same time, the knowledge base has been updated to May 2025, allowing users to accurately access information up to that point even without an internet connection.
DeepSeek updated its web and app on Feb 11, officially announcing a new long-text model test on Feb 14, supporting up to 1M tokens and updated knowledge base to May 2025. API remains V3.2 with 128K context, seen as a prelude to the upcoming V4 model.....
The Ima web version is officially launched. Users can access the knowledge base through a browser, solving issues with software downloads and system compatibility. The new version supports features such as highlighted notes and pop-up Q&A, making it more convenient and efficient. The team will continue to introduce convenient features, and users can mark it as a favorite to stay updated. The web version makes accessing knowledge more flexible and efficient, suitable for various usage scenarios.
In the rapidly evolving landscape of Artificial Intelligence (AI), specialized knowledge for technology professionals is becoming increasingly crucial. Interview Kickstart, based in Santa Clara, California, recently announced an update to its Generative AI course, designed to equip tech professionals to navigate this rapidly changing market. This news coincides with the significant attention generated by Chinese tech giant Baidu's launch of its next-generation AI models – Ernie4.5 and Ernie X1. Baidu's multimodal foundation models...
Huawei
-
Input tokens/M
Output tokens/M
128
Context Length
Tencent
24
32
Iflytek
$2
8
Baidu
$1.5
$6
Openai
$525
$1050
$0.5
250
Deepseek
$1
Alibaba
$18
6
MEMEX is a knowledge management server based on the MCP protocol, used to manage technical guides and AI context, providing functions for creation, search, update, and deletion, and supporting semantic search and integration with Claude AI
This project includes two servers based on the Model Context Protocol (MCP): an IoT device control server and a memory management server. The IoT server provides device control, status query, and real-time update functions, suitable for scenarios such as smart homes and industrial IoT; the memory management server provides long-term memory storage and semantic search functions, suitable for fields such as conversation history and knowledge management.
The WikiJS MCP Server is a tool that connects Claude to the Wiki.js knowledge base, allowing Claude to search, read, update, and create Wiki.js document pages for automated management of the team's knowledge base.
The Insights Knowledge Base (IKB) MCP Server is a plug-and-play free knowledge base with over 10,000 high-quality insight reports built-in. It supports local secure storage and private document parsing. The project has optimized data processing efficiency, provides weekly report updates, and plans to integrate embedding models and enhance the report system in the future.
This is a knowledge base management tool based on the MCP server, which provides a list of knowledge base content and retrieval functions, and supports semantic search and automatic index updates.
A template repository containing a development container for running a local LLM and knowledge base, supporting the addition of git repositories via git subtree or git submodule and updates through the MCP client/server relationship (e.g., VS Code extensions and the Obsidian - MCP server).