News
How to Integrate DeepSeek with LlamaIndex: RAG, Query Engines, and Agents - DeepSeek AI
1+ day, 8+ hour ago (1583+ words) LlamaIndex is a data framework designed specifically for connecting large language models to external data sources. Where other frameworks focus on general-purpose LLM chaining, LlamaIndex excels at indexing, retrieving, and querying your own documents " making it the go-to choice for…...
DeepSeek + Dify: Build and Deploy AI Applications with Visual Workflows - DeepSeek AI
22+ hour, 46+ min ago (938+ words) Dify has native DeepSeek support in its Model Providers. Add your API key, select deepseek-chat or deepseek-reasoner, and you have a functional AI application in under three minutes. But the real value is what comes next: connecting a knowledge base…...
DeepSeek Context Caching Explained - DeepSeek AI
1+ day, 4+ hour ago (1753+ words) DeepSeek Context Caching is a built-in API feature that automatically reuses repeated prompt prefixes across requests. It does not store memory or conversations. Instead, it reduces input cost and latency when you resend the same front-loaded context. Last verified: April…...
DeepSeek Thinking Mode - DeepSeek AI
2+ day, 15+ hour ago (1316+ words) Last verified: April 4, 2026 DeepSeek's current "Your First API Call" and Models & Pricing pages also make the current alias mapping explicit: deepseek-chat is the non-thinking path of DeepSeek-V3.2, while deepseek-reasoner is the thinking path of DeepSeek-V3.2. That is the key architectural…...
How to Build a Production-Ready Website Support Chatbot with DeepSeek API - DeepSeek AI
6+ mon, 1+ week ago (1714+ words) Last verified: April 4, 2026, against the current DeepSeek API docs and the current openai-python README. A website support bot is usually the right first DeepSeek integration because it has a narrow job, clear boundaries, and measurable success. It can answer pricing,…...
DeepSeek on llama.cpp (GGUF): CPU/Mac Guide + Quantization Picks
1+ mon, 2+ week ago (1743+ words) DeepSeek is an open-weight large language model family designed with a focus on reasoning and structured outputs. Some variants support extended context lengths depending on the specific release. Unlike many proprietary models, DeepSeek's weights are freely available under an open…...