DeepSeek This is a new experimental architecture for a llm powered internet scale retrieval engine. This architecture is very different from current research agents, which are designed as answer engines. You can see some example results here: https://deep-seek.vercel.app/ (Note that this won't let you do real queries, since I won't be able to afford it 😅) The main difference between the 2 concepts breaks down to: Answer engine: aggregate a ton of sources to find the one correct answer. This is what "research agents" have converged on recently.
| Stars | 510 |
| Forks | 54 |
| Language | TypeScript |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 41.25/100 |
| Open Issues | 3 |
| Last Updated | 2024-05-07 |
| Created | 2024-03-16 |
| Platforms | node |
| Est. Tokens | ~79k |
Explore other popular ai 工具 tools:
deep-seek is LLM powered retrieval engine designed to process a ton of sources to collect a comprehensive list of entities.. It is categorized as a AI 工具 with 510 GitHub stars.
deep-seek is primarily written in TypeScript. It covers topics such as agent, agentic, ai.
You can find installation instructions and usage details in the deep-seek GitHub repository at github.com/dzhng/deep-seek. The project has 510 stars and 54 forks, indicating an active community.
deep-seek is released under the MIT license, making it free to use and modify according to the license terms.