ollama: add validate_model_on_init, catch more errors (#31784)

* Ensure access to local model during `ChatOllama` instantiation
(#27720). This adds a new param `validate_model_on_init` (default:
`true`)
* Catch a few more errors from the Ollama client to assist users
This commit is contained in:
Mason Daugherty
2025-07-03 11:07:11 -04:00
committed by GitHub
parent 1a3a8db3c9
commit 572020c4d8
10 changed files with 188 additions and 3 deletions

View File

@@ -363,7 +363,7 @@ typing = [
[[package]]
name = "langchain-ollama"
version = "0.3.4"
version = "0.3.3"
source = { editable = "." }
dependencies = [
{ name = "langchain-core" },