| Example | Description |
|---|---|
| Ollama Basic | Run a local Llama 3.1 agent on Ollama in sync, async, and streaming modes. |
| DB | Ollama model example. |
| Ollama Demo DeepSeek R1 | Ask a local DeepSeek-R1 model to write Python for quadratic equations and explain its reasoning. |
| Ollama Demo Gemma | Stream a short story about a local image from Gemma 3 12B running on Ollama. |
| Ollama Demo Phi4 | Run Microsoft Phi-4 locally through Ollama with a one-shot story prompt. |
| Ollama Demo Qwen | Build an NVDA stock report with Qwen3 on Ollama using YFinanceTools. |
| Ollama Image Agent | Describe a local image file with Llama 3.2 Vision running on Ollama. |
| Knowledge | Search a PgVector knowledge base embedded with OllamaEmbedder from a local Llama agent. |
| Memory | Persist user memories and session summaries in Postgres with a local qwen2.5 Ollama agent. |
| Ollama Cloud | Chat Ollama Cloud. |
| Ollama Reasoning Agent | Enable reasoning on a local gpt-oss 120B agent and display the thinking steps. |
| Retry | Review retry settings and why invalid model IDs cannot reliably exercise the retry path. |
| Set Client | Print the response in the terminal. |
| Ollama Set Temperature | Set sampling temperature on an Ollama model through the options dict. |
| Ollama Structured Output | Return a MovieScript Pydantic object from a local Llama 3.2 model on Ollama. |
| Tool Use | Ollama model example. |