steve/go-llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(v2): update CLAUDE.md for native Ollama provider
CI / Lint (push) Failing after 32s
Details
CI / Root Module (push) Failing after 35s
Details
CI / V2 Module (push) Successful in 1m55s
Details

Browse Source
This commit is contained in:
Steve Dudenhoeffer
2026-05-01 18:31:00 +00:00
parent 012c11b775
commit 5d4c4f91af
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
v2/CLAUDE.md
+2
View File
@@ -17,6 +17,7 @@
- Root package `llm` — public API (Client, Model, Chat, ToolBox, Message types) - Root package `llm` — public API (Client, Model, Chat, ToolBox, Message types)
- `provider/` — Provider interface that backends implement - `provider/` — Provider interface that backends implement
- `openai/`, `anthropic/`, `google/` — Provider implementations - `openai/`, `anthropic/`, `google/` — Provider implementations
- `ollama/` — Native `/api/chat` provider, used by both `llm.Ollama()` (local) and `llm.OllamaCloud(apiKey)` (cloud).
- `tools/` — Ready-to-use sample tools (WebSearch, Browser, Exec, ReadFile, WriteFile, HTTP) - `tools/` — Ready-to-use sample tools (WebSearch, Browser, Exec, ReadFile, WriteFile, HTTP)
- `sandbox/` — Isolated Linux container environments via Proxmox LXC + SSH - `sandbox/` — Isolated Linux container environments via Proxmox LXC + SSH
- `internal/schema/` — JSON Schema generation from Go structs - `internal/schema/` — JSON Schema generation from Go structs
@@ -30,3 +31,4 @@
5. MCP one-call connect: `MCPStdioServer(ctx, cmd, args...)` 5. MCP one-call connect: `MCPStdioServer(ctx, cmd, args...)`
6. Streaming via pull-based `StreamReader.Next()` 6. Streaming via pull-based `StreamReader.Next()`
7. Middleware for logging, retry, timeout, usage tracking 7. Middleware for logging, retry, timeout, usage tracking
8. Ollama uses the native `/api/chat` API rather than the OpenAI-compat `/v1` endpoint. Native API supports `think: false` for thinking-capable models, has more reliable tool calling, and is approximately 15-20% lower latency. Both local and cloud share the same provider; only the apiKey/baseURL differ. `llm.Ollama()` targets `http://localhost:11434` with no Authorization header; `llm.OllamaCloud(key)` targets `https://ollama.com` with `Authorization: Bearer <key>`.