tokenator 0.1.10__tar.gz → 0.1.11__tar.gz

{tokenator-0.1.10 → tokenator-0.1.11}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: tokenator
-Version: 0.1.10
+Version: 0.1.11
 Summary: Token usage tracking wrapper for LLMs
 License: MIT
 Author: Ujjwal Maheshwari
@@ -20,12 +20,12 @@ Requires-Dist: requests (>=2.32.3,<3.0.0)
 Requires-Dist: sqlalchemy (>=2.0.0,<3.0.0)
 Description-Content-Type: text/markdown
 
-# Tokenator : Easiest way to track and analyze LLM token usage and cost
+# Tokenator : Track and analyze LLM token usage and cost
 
 Have you ever wondered about :
 - How many tokens does your AI agent consume? 
 - How much does it cost to do run a complex AI workflow with multiple LLM providers?
-- How much money did I spent today on development?
+- How much money/tokens did you spend today on developing with LLMs?
 
 Afraid not, tokenator is here! With tokenator's easy to use API, you can start tracking LLM usage in a matter of minutes.
 
@@ -57,6 +57,9 @@ response = client.chat.completions.create(
 )
 ```
 
+Works with AsyncOpenAI and `streaming=True` as well!
+Note : When streaming, don't forget to add `stream_options={"include_usage": True}` to the `create()` call!
+
 ### Cost Analysis
 
 ```python
@@ -120,6 +123,56 @@ print(cost.last_hour().model_dump_json(indent=4))
 - Minimal memory footprint
 - Minimal latency footprint
 
+### Anthropic
+
+```python
+from anthropic import Anthropic, AsyncAnthropic
+from tokenator import tokenator_anthropic
+
+anthropic_client = AsyncAnthropic(api_key="your-api-key")
+
+# Wrap it with Tokenator
+client = tokenator_anthropic(anthropic_client)
+
+# Use it exactly like the Anthropic client
+response = await client.messages.create(
+    model="claude-3-5-haiku-20241022",
+    messages=[{"role": "user", "content": "hello how are you"}],
+    max_tokens=20,
+)
+
+print(response)
+
+print(usage.last_execution().model_dump_json(indent=4))
+"""
+{
+    "total_cost": 0.0001,
+    "total_tokens": 23,
+    "prompt_tokens": 10,
+    "completion_tokens": 13,
+    "providers": [
+        {
+            "total_cost": 0.0001,
+            "total_tokens": 23,
+            "prompt_tokens": 10,
+            "completion_tokens": 13,
+            "provider": "anthropic",
+            "models": [
+                {
+                    "total_cost": 0.0004,
+                    "total_tokens": 79,
+                    "prompt_tokens": 52,
+                    "completion_tokens": 27,
+                    "model": "claude-3-5-haiku-20241022"
+                }
+            ]
+        }
+    ]
+}
+"""
+```
+---
+
 Most importantly, none of your data is ever sent to any server.
 
 ## License

{tokenator-0.1.10 → tokenator-0.1.11}/README.md

@@ -1,9 +1,9 @@
-# Tokenator : Easiest way to track and analyze LLM token usage and cost
+# Tokenator : Track and analyze LLM token usage and cost
 
 Have you ever wondered about :
 - How many tokens does your AI agent consume? 
 - How much does it cost to do run a complex AI workflow with multiple LLM providers?
-- How much money did I spent today on development?
+- How much money/tokens did you spend today on developing with LLMs?
 
 Afraid not, tokenator is here! With tokenator's easy to use API, you can start tracking LLM usage in a matter of minutes.
 
@@ -35,6 +35,9 @@ response = client.chat.completions.create(
 )
 ```
 
+Works with AsyncOpenAI and `streaming=True` as well!
+Note : When streaming, don't forget to add `stream_options={"include_usage": True}` to the `create()` call!
+
 ### Cost Analysis
 
 ```python
@@ -98,6 +101,56 @@ print(cost.last_hour().model_dump_json(indent=4))
 - Minimal memory footprint
 - Minimal latency footprint
 
+### Anthropic
+
+```python
+from anthropic import Anthropic, AsyncAnthropic
+from tokenator import tokenator_anthropic
+
+anthropic_client = AsyncAnthropic(api_key="your-api-key")
+
+# Wrap it with Tokenator
+client = tokenator_anthropic(anthropic_client)
+
+# Use it exactly like the Anthropic client
+response = await client.messages.create(
+    model="claude-3-5-haiku-20241022",
+    messages=[{"role": "user", "content": "hello how are you"}],
+    max_tokens=20,
+)
+
+print(response)
+
+print(usage.last_execution().model_dump_json(indent=4))
+"""
+{
+    "total_cost": 0.0001,
+    "total_tokens": 23,
+    "prompt_tokens": 10,
+    "completion_tokens": 13,
+    "providers": [
+        {
+            "total_cost": 0.0001,
+            "total_tokens": 23,
+            "prompt_tokens": 10,
+            "completion_tokens": 13,
+            "provider": "anthropic",
+            "models": [
+                {
+                    "total_cost": 0.0004,
+                    "total_tokens": 79,
+                    "prompt_tokens": 52,
+                    "completion_tokens": 27,
+                    "model": "claude-3-5-haiku-20241022"
+                }
+            ]
+        }
+    ]
+}
+"""
+```
+---
+
 Most importantly, none of your data is ever sent to any server.
 
 ## License

{tokenator-0.1.10 → tokenator-0.1.11}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "tokenator"
-version = "0.1.10"
+version = "0.1.11"
 description = "Token usage tracking wrapper for LLMs"
 authors = ["Ujjwal Maheshwari <your.email@example.com>"]
 readme = "README.md"

{tokenator-0.1.10 → tokenator-0.1.11}/src/tokenator/anthropic/client_anthropic.py

@@ -71,7 +71,6 @@ def _create_usage_callback(execution_id, log_usage_fn):
                 usage_data.usage.prompt_tokens += chunk.message.usage.input_tokens
                 usage_data.usage.completion_tokens += chunk.message.usage.output_tokens
             elif isinstance(chunk, RawMessageDeltaEvent):
-                usage_data.usage.prompt_tokens += chunk.usage.input_tokens
                 usage_data.usage.completion_tokens += chunk.usage.output_tokens
         
         usage_data.usage.total_tokens = usage_data.usage.prompt_tokens + usage_data.usage.completion_tokens

{tokenator-0.1.10 → tokenator-0.1.11}/src/tokenator/base_wrapper.py

@@ -47,7 +47,7 @@ class BaseWrapper:
                 total_tokens=token_usage_stats.usage.total_tokens,
             )
             session.add(token_usage)
-            logger.info(
+            logger.debug(
                 "Logged token usage: model=%s, total_tokens=%d",
                 token_usage_stats.model,
                 token_usage_stats.usage.total_tokens,