v3

Author: siddharthsambharia-portkey

images/supported-llm/lepton.png

@@ -685,6 +685,30 @@ set_default_openai_client(portkey)
 ```
 
 
+
+
+**Filter Analytics by User**
+
+With metadata in place, you can filter analytics by user and analyze performance metrics on a per-user basis:
+
+<Frame caption="Filter analytics by user">
+  <img src="/images/metadata-filters.png"/>
+</Frame>
+
+
+This enables:
+- Per-user cost tracking and budgeting
+- Personalized user analytics
+- Team or organization-level metrics
+- Environment-specific monitoring (staging vs. production)
+
+<Card title="Learn More About Metadata" icon="tags" href="/product/observability/metadata">
+  Explore how to use custom metadata to enhance your analytics
+</Card>
+
+
+
+
 ### 6. Caching for Efficient Agents
 
 Implement caching to make your OpenAI Agents agents more efficient and cost-effective:
@@ -737,25 +761,75 @@ Implement caching to make your OpenAI Agents agents more efficient and cost-effe
 </Tabs>
 
 
-**Filter Analytics by User**
 
-With metadata in place, you can filter analytics by user and analyze performance metrics on a per-user basis:
 
-<Frame caption="Filter analytics by user">
-  <img src="/images/metadata-filters.png"/>
-</Frame>
+### 7. Model Interoperability
 
+With Portkey, you can easily switch between different LLMs in your OpenAI Agents without changing your core agent logic.
 
-This enables:
-- Per-user cost tracking and budgeting
-- Personalized user analytics
-- Team or organization-level metrics
-- Environment-specific monitoring (staging vs. production)
+```python
+# Configure Portkey with different LLM providers
+from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
+from openai import AsyncOpenAI
+from agents import set_default_openai_client
 
-<Card title="Learn More About Metadata" icon="tags" href="/product/observability/metadata">
-  Explore how to use custom metadata to enhance your analytics
+# Using OpenAI
+openai_config = {
+    "provider": "openai",
+    "api_key": "YOUR_OPENAI_API_KEY",
+    "override_params": {
+        "model": "gpt-4o"
+    }
+}
+
+# Using Anthropic
+anthropic_config = {
+    "provider": "anthropic",
+    "api_key": "YOUR_ANTHROPIC_API_KEY",
+    "override_params": {
+        "model": "claude-3-opus-20240229"
+    }
+}
+
+# Choose which config to use
+active_config = openai_config  # or anthropic_config
+
+# Configure OpenAI client with chosen provider
+portkey = AsyncOpenAI(
+    base_url=PORTKEY_GATEWAY_URL,
+    api_key=os.environ["PORTKEY_API_KEY"],
+    default_headers=createHeaders(config=active_config)
+)
+set_default_openai_client(portkey)
+
+# Create and run agent - no changes needed in agent code
+agent = Agent(
+    name="Assistant",
+    instructions="You are a helpful assistant.",
+    # The model specified here will be used as a reference but the actual model
+    # is determined by the active_config
+    model="gpt-4o"
+)
+
+result = Runner.run_sync(agent, "Tell me about quantum computing.")
+print(result.final_output)
+```
+
+Portkey provides access to over 200 LLMs through a unified interface, including:
+
+- OpenAI (GPT-4o, GPT-4 Turbo, etc.)
+- Anthropic (Claude 3.5 Sonnet, Claude 3 Opus, etc.)
+- Mistral AI (Mistral Large, Mistral Medium, etc.)
+- Google Vertex AI (Gemini 1.5 Pro, etc.)
+- Cohere (Command, Command-R, etc.)
+- AWS Bedrock (Claude, Titan, etc.)
+- Local/Private Models
+
+<Card title="Supported Providers" icon="server" href="/integrations/llms">
+  See the full list of LLM providers supported by Portkey
 </Card>
 
+
 ## Tool Use in OpenAI Agents
 
 OpenAI Agents SDK natively supports tools that enable your agents to interact with external systems and APIs. Portkey provides full observability for tool usage in your agents:
@@ -836,74 +910,6 @@ print(result.final_output)
 
 
 
-## Model Interoperability
-
-With Portkey, you can easily switch between different LLMs in your OpenAI Agents without changing your core agent logic.
-
-```python
-# Configure Portkey with different LLM providers
-from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
-from openai import AsyncOpenAI
-from agents import set_default_openai_client
-
-# Using OpenAI
-openai_config = {
-    "provider": "openai",
-    "api_key": "YOUR_OPENAI_API_KEY",
-    "override_params": {
-        "model": "gpt-4o"
-    }
-}
-
-# Using Anthropic
-anthropic_config = {
-    "provider": "anthropic",
-    "api_key": "YOUR_ANTHROPIC_API_KEY",
-    "override_params": {
-        "model": "claude-3-opus-20240229"
-    }
-}
-
-# Choose which config to use
-active_config = openai_config  # or anthropic_config
-
-# Configure OpenAI client with chosen provider
-portkey = AsyncOpenAI(
-    base_url=PORTKEY_GATEWAY_URL,
-    api_key=os.environ["PORTKEY_API_KEY"],
-    default_headers=createHeaders(config=active_config)
-)
-set_default_openai_client(portkey)
-
-# Create and run agent - no changes needed in agent code
-agent = Agent(
-    name="Assistant",
-    instructions="You are a helpful assistant.",
-    # The model specified here will be used as a reference but the actual model
-    # is determined by the active_config
-    model="gpt-4o"
-)
-
-result = Runner.run_sync(agent, "Tell me about quantum computing.")
-print(result.final_output)
-```
-
-Portkey provides access to over 200 LLMs through a unified interface, including:
-
-- OpenAI (GPT-4o, GPT-4 Turbo, etc.)
-- Anthropic (Claude 3.5 Sonnet, Claude 3 Opus, etc.)
-- Mistral AI (Mistral Large, Mistral Medium, etc.)
-- Google Vertex AI (Gemini 1.5 Pro, etc.)
-- Cohere (Command, Command-R, etc.)
-- AWS Bedrock (Claude, Titan, etc.)
-- Local/Private Models
-
-<Card title="Supported Providers" icon="server" href="/integrations/llms">
-  See the full list of LLM providers supported by Portkey
-</Card>
-
-
-
 
 
 ## Set Up Enterprise Governance for OpenAI Agents

integrations/agents/openai-agents.mdx

@@ -95,6 +95,11 @@ description: "Portkey connects with all major LLM providers and orchestration fr
       <Frame><img src="/images/supported-llm/lemonfox-ai.png" alt="Lemonfox AI" /></Frame>
     </Card>
 
+
+    <Card title="Lepton AI" href="/integrations/llms/lepton">
+      <Frame><img src="/images/supported-llm/lepton.png" alt="Lepton AI" /></Frame>
+    </Card>
+
     <Card title="Lingyi (01.ai)" href="/integrations/llms/lingyi-01.ai">
       <Frame><img src="/images/supported-llm/lingyi.png" alt="Lingyi (01.ai)" /></Frame>
     </Card>

integrations/llms.mdx

@@ -101,35 +101,6 @@ Use the Portkey instance to send requests to Lepton AI. You can also override th
     </Tab>
 </Tabs>
 
-## Text Completions
-
-For applications that require the traditional completions API, you can use Lepton AI's completions endpoint.
-
-<Tabs>
-    <Tab title="NodeJS SDK">
-        ```js
-        const completion = await portkey.completions.create({
-            prompt: 'Write a poem about AI',
-            model: 'llama-3-8b-sft-v1',
-            max_tokens: 250
-        });
-
-        console.log(completion.choices);
-        ```
-    </Tab>
-    <Tab title="Python SDK">
-        ```python
-        completion = portkey.completions.create(
-            prompt="Write a poem about AI",
-            model="llama-3-8b-sft-v1",
-            max_tokens=250
-        )
-
-        print(completion)
-        ```
-    </Tab>
-</Tabs>
-
 ## Speech-to-Text (Transcription)
 
 Lepton AI provides speech-to-text capabilities through Portkey's unified API:
@@ -195,45 +166,6 @@ Lepton AI supports streaming responses to provide real-time generation:
     </Tab>
 </Tabs>
 
-### Lepton-Specific Parameters
-
-Lepton AI models support several unique parameters for advanced control:
-
-- `length_penalty`: Controls the length of generated text (default: 1)
-- `repetition_penalty`: Reduces repetitive patterns in generation (default: 1)
-- `dry_multiplier`: Controls monotonicity of text (default: 0)
-- `top_k`: Number of highest probability tokens to consider (default: 50)
-- `min_p`: Filters out tokens below a probability threshold (default: 0)
-
-Example with custom parameters:
-
-```python
-completion = portkey.chat.completions.create(
-    messages=[{"role": "user", "content": "Write a creative story"}],
-    model="llama-3-8b-sft-v1",
-    temperature=0.8,
-    top_p=0.95,
-    repetition_penalty=1.2,
-    length_penalty=1.1,
-    top_k=40,
-    min_p=0.05
-)
-```
-
-### Audio Support
-
-Lepton AI offers specialized audio features:
-
-```python
-completion = portkey.chat.completions.create(
-    messages=[{"role": "user", "content": "Generate a spoken response"}],
-    model="llama-3-8b-sft-v1",
-    require_audio=True,
-    tts_preset_id="jessica",  # Voice ID
-    tts_audio_format="mp3",   # Output format
-    tts_audio_bitrate=64      # Quality setting
-)
-```
 
 ## Managing Lepton AI Prompts