pin dependencies

add pseudo API key so the client doesn't raise an error
this seems to have been introduced in a recent OpenAI SDK update
2026-06-14 18:03:54 +02:00 · 2026-06-14 18:00:42 +02:00 · 2026-06-03 18:22:06 +02:00
3 changed files with 6 additions and 6 deletions
@@ -1,5 +1,5 @@
 {
-    "title": "llama.cpp inference",
+    "title": "llama.cpp",
    "description": "Run llama.cpp inference using serverless RunPod workers!",
    "type": "serverless",
    "category": "language",
@@ -28,7 +28,7 @@ from utils import JobInput
 client = OpenAI(
    base_url="http://localhost:3098/v1/",
-    api_key="",
+    api_key="none",
 )
@@ -1,3 +1,3 @@
-runpod
+runpod==1.9.1
-python-dotenv
+python-dotenv==1.2.2
-openai
+openai==2.41.1
Author	SHA1	Message	Date
MagnusandGitHub	029f37afab	pin dependencies	2026-06-14 18:03:54 +02:00
MagnusandGitHub	85c10953d6	add pseudo API key so the client doesn't raise an error this seems to have been introduced in a recent OpenAI SDK update	2026-06-14 18:00:42 +02:00
MagnusandGitHub	ea82e2a901	remove "inference" from title to make it more consistent with the other runpod repos on the hub	2026-06-03 18:22:06 +02:00