Restore structure and place litellm integraton under model_providers

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

README.md

@@ -178,31 +178,3 @@ We'd like to acknowledge the excellent work of the open-source community, especi
 -   [uv](https://github.com/astral-sh/uv) and [ruff](https://github.com/astral-sh/ruff)
 
 We're committed to continuing to build the Agents SDK as an open source framework so others in the community can expand on our approach.
-
-
-## LiteLLM Proxy Server integration
-
-```bash
-# launch proxy
-litellm --config config.yaml
-```
-
-Testing some basic models against proxy to verify it's operational:
-```bash
-# qwen2.5:14b
-curl -s http://localhost:4000/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "qwen2.5:14b", "messages": [{"role": "user", "content": "Say hi"}], "max_tokens": 10}' | jq
-
-# claude-3-7
-curl -s http://localhost:4000/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "claude-3-7", "messages": [{"role": "user", "content": "Say hi"}], "max_tokens": 10}' | jq
-
-# gpt-4o
-curl -s http://localhost:4000/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Say hi"}], "max_tokens": 10}' | jq
-```
-
-Launch the Agents SDK with the proxy server:
-```bash
-python3 examples/agent_patterns/litellm.py
-```
-
-Additional docs:
-- LiteLLM admin UI https://docs.litellm.ai/docs/proxy/ui

examples/model_providers/README.md

@@ -17,3 +17,29 @@ Loops within themselves,
 Function calls its own being,
 Depth without ending.
 ```
+
+
+## LiteLLM Proxy Server integration
+
+LiteLLM integration helps out switch between models easily and rapidly. This is easy to integrate via `AsyncOpenAI`:
+
+```bash
+# launch server proxy with your configuration
+litellm --config examples/model_providers/litellm_config.yaml
+
+# then use the proxy via the SDK
+python3 examples/agent_patterns/litellm.py
+```
+
+### Testing the proxy server
+Testing some basic models against proxy to verify it's operational:
+```bash
+# qwen2.5:14b
+curl -s http://localhost:4000/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "qwen2.5:14b", "messages": [{"role": "user", "content": "Say hi"}], "max_tokens": 10}' | jq
+
+# claude-3-7
+curl -s http://localhost:4000/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "claude-3-7", "messages": [{"role": "user", "content": "Say hi"}], "max_tokens": 10}' | jq
+
+# gpt-4o
+curl -s http://localhost:4000/v1/chat/completions -H "Content-Type: application/json" -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Say hi"}], "max_tokens": 10}' | jq
+```

examples/model_providers/litellm.py

@@ -1,18 +1,23 @@
+import os
+from dotenv import load_dotenv
 from openai import AsyncOpenAI
 from agents import OpenAIChatCompletionsModel,Agent,Runner
 from agents.model_settings import ModelSettings
 from agents import set_default_openai_client, set_tracing_disabled
 
+# Load environment variables from .env file
+load_dotenv()
+
 external_client = AsyncOpenAI(
-    base_url = 'http://localhost:4000',
-    api_key="cai")
+    base_url = os.getenv('LITELLM_BASE_URL', 'http://localhost:4000'),
+    api_key=os.getenv('LITELLM_API_KEY', 'key'))
 
 set_default_openai_client(external_client)
 set_tracing_disabled(True)
 
-# llm_model="qwen2.5:14b"
-# llm_model="claude-3-7"
-llm_model="gpt-4o"
+llm_model=os.getenv('LLM_MODEL', 'gpt-4o')
+# llm_model=os.getenv('LLM_MODEL', 'claude-3-7')
+# llm_model=os.getenv('LLM_MODEL', 'qwen2.5:14b')
 
 # For Qwen models, we need to skip system instructions as they're not supported
 instructions = None if "qwen" in llm_model.lower() else "You are a helpful assistant"
@@ -28,8 +33,4 @@ agent = Agent(
 
 
 result = Runner.run_sync(agent, "Write a haiku about recursion in programming.")
-print(result.final_output)
-
-# Code within the code,
-# Functions calling themselves,
-# Infinite loop's dance.
+print(result.final_output)

examples/model_providers/litellm_config.yaml

@@ -1,14 +1,14 @@
 model_list:
-  - model_name: claude-3-7
-    litellm_params: 
-      model: claude-3-7-sonnet-20250219
-      api_key: "os.environ/ANTHROPIC_API_KEY" # does os.getenv("ANTHROPIC_API_KEY")
-      base_url: 'https://api.anthropic.com'
   - model_name: gpt-4o
     litellm_params:
       model: gpt-4o
       api_key: "os.environ/OPENAI_API_KEY"
       api_base: https://api.openai.com/v1
+  - model_name: claude-3-7
+    litellm_params: 
+      model: claude-3-7-sonnet-20250219
+      api_key: "os.environ/ANTHROPIC_API_KEY" # does os.getenv("ANTHROPIC_API_KEY")
+      base_url: 'https://api.anthropic.com'
   - model_name: qwen2.5:14b
     litellm_params:
       model: ollama/qwen2.5:14b