Fix use other chat completion providers (#2153)

* Fix: use other LLMs providers for chat completion * lint
huggingface · Mar 25, 2024 · 9e13b83 · 9e13b83
1 parent 59be8f2
commit 9e13b83
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 2 deletions.
diff --git a/src/huggingface_hub/inference/_client.py b/src/huggingface_hub/inference/_client.py
@@ -548,7 +548,9 @@ def chat_completion(
         if _is_chat_completion_server(model):
             # First, let's consider the server has a `/v1/chat/completions` endpoint.
             # If that's the case, we don't have to render the chat template client-side.
-            model_url = self._resolve_url(model) + "/v1/chat/completions"
+            model_url = self._resolve_url(model)
+            if not model_url.endswith("/chat/completions"):
+                model_url += "/v1/chat/completions"
 
             try:
                 data = self.post(

diff --git a/src/huggingface_hub/inference/_generated/_async_client.py b/src/huggingface_hub/inference/_generated/_async_client.py
@@ -548,7 +548,9 @@ async def chat_completion(
         if _is_chat_completion_server(model):
             # First, let's consider the server has a `/v1/chat/completions` endpoint.
             # If that's the case, we don't have to render the chat template client-side.
-            model_url = self._resolve_url(model) + "/v1/chat/completions"
+            model_url = self._resolve_url(model)
+            if not model_url.endswith("/chat/completions"):
+                model_url += "/v1/chat/completions"
 
             try:
                 data = await self.post(