llama-index-llms-openai 0.1.28__tar.gz → 0.1.30__tar.gz

{llama_index_llms_openai-0.1.28 → llama_index_llms_openai-0.1.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-index-llms-openai
-Version: 0.1.28
+Version: 0.1.30
 Summary: llama-index llms openai integration
 License: MIT
 Author: llama-index

{llama_index_llms_openai-0.1.28 → llama_index_llms_openai-0.1.30}/llama_index/llms/openai/base.py

@@ -604,18 +604,29 @@ class OpenAI(FunctionCallingLLM):
 
     def _get_response_token_counts(self, raw_response: Any) -> dict:
         """Get the token usage reported by the response."""
-        if not isinstance(raw_response, dict):
-            return {}
-
-        usage = raw_response.get("usage", {})
-        # NOTE: other model providers that use the OpenAI client may not report usage
-        if usage is None:
+        if hasattr(raw_response, "usage"):
+            try:
+                prompt_tokens = raw_response.usage.prompt_tokens
+                completion_tokens = raw_response.usage.completion_tokens
+                total_tokens = raw_response.usage.total_tokens
+            except AttributeError:
+                return {}
+        elif isinstance(raw_response, dict):
+            usage = raw_response.get("usage", {})
+            # NOTE: other model providers that use the OpenAI client may not report usage
+            if usage is None:
+                return {}
+            # Backwards compatibility with old dict type
+            prompt_tokens = usage.get("prompt_tokens", 0)
+            completion_tokens = usage.get("completion_tokens", 0)
+            total_tokens = usage.get("total_tokens", 0)
+        else:
             return {}
 
         return {
-            "prompt_tokens": usage.get("prompt_tokens", 0),
-            "completion_tokens": usage.get("completion_tokens", 0),
-            "total_tokens": usage.get("total_tokens", 0),
+            "prompt_tokens": prompt_tokens,
+            "completion_tokens": completion_tokens,
+            "total_tokens": total_tokens,
         }
 
     # ===== Async Endpoints =====

{llama_index_llms_openai-0.1.28 → llama_index_llms_openai-0.1.30}/llama_index/llms/openai/utils.py

@@ -47,6 +47,7 @@ GPT4_MODELS: Dict[str, int] = {
     "gpt-4-turbo": 128000,
     "gpt-4o": 128000,
     "gpt-4o-2024-05-13": 128000,
+    "gpt-4o-2024-08-06": 128000,
     "gpt-4o-mini": 128000,
     "gpt-4o-mini-2024-07-18": 128000,
     # 0613 models (function calling):

{llama_index_llms_openai-0.1.28 → llama_index_llms_openai-0.1.30}/pyproject.toml

@@ -29,7 +29,7 @@ exclude = ["**/BUILD"]
 license = "MIT"
 name = "llama-index-llms-openai"
 readme = "README.md"
-version = "0.1.28"
+version = "0.1.30"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"