update

llm/deepinfra_api.py

@@ -25,7 +25,7 @@ class DeepInfraApi(LlmApi):
         """
         try:
             async with httpx.AsyncClient() as client:
-                response = await client.get(f"{self.params.url}/v1/openai/models", super().create_headers())
+                response = await client.get(f"{self.params.url}/v1/openai/models", headers=super().create_headers())
                 if response.status_code == 200:
                     json_data = response.json()
                     return [item['id'] for item in json_data.get('data', [])]
@@ -148,6 +148,6 @@ class DeepInfraApi(LlmApi):
             request = await self.create_request(prompt)
 
             async with httpx.AsyncClient() as client:
-                response = client.post(f"{self.params.url}/v1/openai/chat/completions", super().create_headers(), json=request)
+                response = client.post(f"{self.params.url}/v1/openai/chat/completions", headers=super().create_headers(), json=request)
                 if response.status_code == 200:
                     return response.json()["choices"][0]["message"]["content"]

llm/vllm_api.py

@@ -27,7 +27,7 @@ class LlmApi(LlmApi):
         """
         try:
             async with httpx.AsyncClient() as client:
-                response = await client.get(f"{self.params.url}/v1/models", super().create_headers())
+                response = await client.get(f"{self.params.url}/v1/models", headers=super().create_headers())
                 if response.status_code == 200:
                     json_data = response.json()
                     return [item['id'] for item in json_data.get('data', [])]