latest and clean integrations docs

Author: dot-agi

docs/v2/integrations/ag2.mdx

@@ -54,19 +54,20 @@ os.environ["AGENTOPS_API_KEY"] = os.getenv("AGENTOPS_API_KEY")
 
 Initialize AgentOps at the beginning of your application to automatically track all AG2 agent interactions:
 
-<CodeGroup>
-```python Python
+<CodeGroup> 
+```python Single Agent Conversation
 import agentops
 import autogen
+import os
 
 # Initialize AgentOps
-agentops.init(<INSERT YOUR API KEY HERE>)
+agentops.init()
 
 # Configure your AG2 agents
 config_list = [
     {
         "model": "gpt-4",
-        "api_key": "<YOUR_OPENAI_API_KEY>"
+        "api_key": os.getenv("OPENAI_API_KEY"),
     }
 ]
 
@@ -75,7 +76,7 @@ llm_config = {
     "timeout": 60,
 }
 
-# Create AG2 agents
+# Create a single agent
 assistant = autogen.AssistantAgent(
     name="assistant",
     llm_config=llm_config,
@@ -95,34 +96,27 @@ user_proxy.initiate_chat(
     assistant,
     message="How can I implement a basic web scraper in Python?"
 )
-
-# All agent interactions are automatically tracked by AgentOps
 ```
-</CodeGroup>
-
-## Multi-Agent Conversation Example
-
-AgentOps tracks interactions across multiple AG2 agents:
 
-<CodeGroup>
-```python Python
+```python Multi-Agent Conversation
+import os
 import agentops
 import autogen
 
 # Initialize AgentOps
-agentops.init(<INSERT YOUR API KEY HERE>)
+agentops.init()
 
-# Configure LLM
+# Configure your AG2 agents
 config_list = [
     {
         "model": "gpt-4",
-        "api_key": "<YOUR_OPENAI_API_KEY>"
+        "api_key": os.getenv("OPENAI_API_KEY"),
     }
 ]
 
 llm_config = {
     "config_list": config_list,
-    "timeout": A 60,
+    "timeout": 60,
 }
 
 # Create a team of agents
@@ -169,8 +163,6 @@ user_proxy.initiate_chat(
     manager,
     message="Create a Python program to analyze sentiment from Twitter data."
 )
-
-# All agent interactions across the group chat are automatically tracked by AgentOps
 ```
 </CodeGroup>
 

docs/v2/integrations/agents_sdk.mdx

@@ -59,44 +59,32 @@ OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 
 ## Usage
 
-Initialize AgentOps at the beginning of your application. It will automatically instrument the OpenAI Agents SDK. The "Hello World Example" below demonstrates basic usage.
+AgentOps will automatically instrument the OpenAI Agents SDK after being initialized. You can then create agents, run them, and track their interactions.
 
-<CodeGroup>
-```python Hello World Example
-from agents import Agent, Runner
+```python
 import agentops
-import os # Ensure os is imported if using os.getenv
-
-# Initialize AgentOps. 
-# If AGENTOPS_API_KEY is in env, it's used. Otherwise, pass it directly.
-# Example: agentops.init(os.getenv("AGENTOPS_API_KEY")) or agentops.init("<YOUR_AGENTOPS_API_KEY>")
-agentops.init() # Assumes AGENTOPS_API_KEY is in environment
+from agents import Agent, Runner
 
-# OpenAI client used by Agents SDK will pick up OPENAI_API_KEY from env.
+# Initialize AgentOps
+agentops.init()
 
+# Create an agent with instructions
 agent = Agent(name="Assistant", instructions="You are a helpful assistant")
 
 result = Runner.run_sync(agent, "Write a haiku about recursion in programming.")
 print(result.final_output)
-
-# Expected Output:
-# Code within the code,
-# Functions calling themselves,
-# Infinite loop's dance.
 ```
-</CodeGroup>
-
-## Advanced Examples
 
-### Handoffs Example
+## Examples
 
-```python
+<CodeGroup>
+```python Handoffs
 from agents import Agent, Runner
 import asyncio
 import agentops
 import os
 
-agentops.init() # Assumes AGENTOPS_API_KEY is in environment
+agentops.init()
 
 spanish_agent = Agent(
     name="Spanish agent",
@@ -125,15 +113,13 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-### Functions Example
-
-```python
+```python Function Calling
 import asyncio
 from agents import Agent, Runner, function_tool
 import agentops
 import os
 
-agentops.init() # Assumes AGENTOPS_API_KEY is in environment
+agentops.init()
 
 @function_tool
 def get_weather(city: str) -> str:
@@ -156,27 +142,9 @@ async def main():
 if __name__ == "__main__":
     asyncio.run(main())
 ```
+</CodeGroup>
 
-## The Agent Loop
-
-When you call `Runner.run()`, the SDK runs a loop until it gets a final output:
-
-1. The LLM is called using the model and settings on the agent, along with the message history.
-2. The LLM returns a response, which may include tool calls.
-3. If the response has a final output, the loop ends and returns it.
-4. If the response has a handoff, the agent is set to the new agent and the loop continues from step 1.
-5. Tool calls are processed (if any) and tool response messages are appended. Then the loop continues from step 1.
-
-You can use the `max_turns` parameter to limit the number of loop executions.
-
-## Final Output
-
-Final output is the last thing the agent produces in the loop:
-
-- If you set an `output_type` on the agent, the final output is when the LLM returns something of that type using structured outputs.
-- If there's no `output_type` (i.e., plain text responses), then the first LLM response without any tool calls or handoffs is considered the final output.
-
-## Examples
+## More Examples
 <CardGroup cols={2}>
   <Card title="Customer Service Agent" icon="notebook" href="/v2/examples/openai_agents">
     Demonstrates a customer service workflow

docs/v2/integrations/anthropic.mdx

@@ -58,107 +58,65 @@ os.environ["AGENTOPS_API_KEY"] = os.getenv("AGENTOPS_API_KEY")
 
 Initialize AgentOps at the beginning of your application to automatically track all Anthropic API calls:
 
-    <CodeGroup>
-```python Basic Usage
+```python
 import agentops
 import anthropic
 
 # Initialize AgentOps
-agentops.init(<INSERT YOUR API KEY HERE>)
+agentops.init()
 
 # Create Anthropic client
-client = anthropic.Anthropic(api_key="<YOUR_ANTHROPIC_API_KEY>")
+client = anthropic.Anthropic()
 
 # Make a completion request - AgentOps will track it automatically
 message = client.messages.create(
-    model="claude-3-opus-20240229",
-    max_tokens=1000,
+    model="claude-sonnet-4-20250514",
     messages=[
         {"role": "user", "content": "What is artificial intelligence?"}
     ]
 )
 
+# Print the response received
 print(message.content[0].text)
-      ```
-    </CodeGroup>
-
-
-## Advanced Examples
+```
 
-### Streaming Example
 
-AgentOps automatically tracks streaming completions:
+## Examples
 
-    <CodeGroup>
-```python Streaming Example
+<CodeGroup>
+```python Streaming
 import agentops
 import anthropic
 
 # Initialize AgentOps
-      agentops.init(<INSERT YOUR API KEY HERE>)
+agentops.init()
 
 # Create Anthropic client
-client = anthropic.Anthropic(api_key="<YOUR_ANTHROPIC_API_KEY>")
+client = anthropic.Anthropic()
 
 # Make a streaming request
 with client.messages.stream(
-    model="claude-3-haiku-20240307",
-    max_tokens=1000,
+    model="claude-sonnet-4-20250514",
     messages=[
         {"role": "user", "content": "Write a short poem about artificial intelligence."}
     ]
 ) as stream:
     for text in stream.text_stream:
         print(text, end="", flush=True)
-    print()  # Add a newline at the end
-      ```
-    </CodeGroup>
-
-### System Prompt Example
-
-AgentOps tracks interactions with system prompts:
-
-      <CodeGroup>
-```python System Prompt
-import agentops
-import anthropic
-
-# Initialize AgentOps
-agentops.init(<INSERT YOUR API KEY HERE>)
-
-# Create Anthropic client
-client = anthropic.Anthropic(api_key="<YOUR_ANTHROPIC_API_KEY>")
-
-# Make a request with a system prompt
-message = client.messages.create(
-    model="claude-3-sonnet-20240229",
-    max_tokens=1000,
-    system="You are a helpful AI assistant with expertise in science and technology. Keep your answers concise and accurate.",
-    messages=[
-        {"role": "user", "content": "Explain quantum computing in simple terms."}
-    ]
-)
-
-print(message.content[0].text)
-        ```
-      </CodeGroup>
-
-### Tool Use Example
-
-AgentOps tracks tool use with Claude:
+    print()
+```
 
-<CodeGroup>
 ```python Tool Use
 import agentops
 import anthropic
 import json
 from datetime import datetime
 
 # Initialize AgentOps
-  agentops.init(<INSERT YOUR API KEY HERE>)
+agentops.init()
 
 # Create Anthropic client
-client = anthropic.Anthropic(api_key="<YOUR_ANTHROPIC_API_KEY>")
+client = anthropic.Anthropic()
 
 # Define tools
 tools = [
@@ -179,8 +137,7 @@ def get_current_time():
 
 # Make a request with tools
   message = client.messages.create(
-      model="claude-3-opus-20240229",
-    max_tokens=1000,
+    model="claude-opus-4-20250514",
     tools=tools,
     messages=[
         {"role": "user", "content": "What time is it now?"}
@@ -197,8 +154,7 @@ if message.content[0].type == "tool_calls":
 
         # Continue the conversation with the tool response
         second_message = client.messages.create(
-          model="claude-3-opus-20240229",
-            max_tokens=1000,
+          model="claude-opus-4-20250514",
             messages=[
                 {"role": "user", "content": "What time is it now?"},
                 {
@@ -230,20 +186,17 @@ else:
 ```
 </CodeGroup>
 
-## Examples
+## More Examples
 
 <CardGroup cols={2}>
   <Card title="Understanding Tools" icon="notebook" href="/v2/examples/anthropic">
     Claude integration with tool usage and advanced features
   </Card>
-  <Card title="Async Example" icon="notebook" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/anthropic/anthropic-example-async.ipynb" newTab={true}>
-    Demonstrates asynchronous calls with the Anthropic SDK.
-  </Card>
   <Card title="Sync Example" icon="notebook" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/anthropic/anthropic-example-sync.ipynb" newTab={true}>
     Shows synchronous calls with the Anthropic SDK.
   </Card>
-  <Card title="Tool Use (Alternative)" icon="notebook" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/anthropic/anthropic-example-tool.ipynb" newTab={true}>
-    Another example of tool usage with Anthropic models.
+  <Card title="Async Example" icon="notebook" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/anthropic/anthropic-example-async.ipynb" newTab={true}>
+    Demonstrates asynchronous calls with the Anthropic SDK.
   </Card>
 </CardGroup>