fix: custom fetch wrapper for ollama inference. Fixes #656 (#1032)

* Add configurable fetch timeout for Ollama client

* Worker service needs access to the .env file

* repair typescript types

* Update customFetch.ts

* update the config docs

---------

Co-authored-by: sbarbett <shane@barbetta.me>
Co-authored-by: Mohamed Bassem <me@mbassem.com>

1 files changed, 2 insertions, 0 deletions

diff --git a/packages/shared/inference.ts b/packages/shared/inference.ts
index e5ddf5ca..92d9dd94 100644
--- a/packages/shared/inference.ts
+++ b/packages/shared/inference.ts
@@ -2,6 +2,7 @@ import { Ollama } from "ollama";
 import OpenAI from "openai";
 
 import serverConfig from "./config";
+import { customFetch } from "./customFetch";
 import logger from "./logger";
 
 export interface InferenceResponse {
@@ -153,6 +154,7 @@ class OllamaInferenceClient implements InferenceClient {
   constructor() {
     this.ollama = new Ollama({
       host: serverConfig.inference.ollamaBaseUrl,
+      fetch: customFetch, // Use the custom fetch with configurable timeout
     });
   }