product · inferred from evidence
Ollama
A server-side product that provides model serving capabilities, including streaming-tool support.
- streaming not working when using bind_tools with ChatOllama - llm.stream() returns no tokens
The root cause was on the Ollama server side, not in LangChain. A reporter confirmed that updating to the latest Ollama release (which shipped streaming-tool support) fixed streaming with bind_tools, and another confirmed the same behavior: