chore: add examples

Author: yanxi0830

.github/CODEOWNERS

@@ -0,0 +1,5 @@
+# Each line is a file pattern followed by one or more owners.
+
+# These owners will be the default owners for everything in
+# the repo. Unless a later match takes precedence,
+* @yanxi0830 @lucidom

.github/workflows/examples.yml

@@ -0,0 +1,92 @@
+name: Run Examples
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:  # Allows manual triggering
+  schedule:
+    - cron: '0 * * * *' # every hour
+
+jobs:
+  chat:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - name: Install dependencies
+      env:
+        GITHUB_TOKEN: ${{ secrets.MY_GITHUB_TOKEN }}
+      run: |
+        git config --global url."https://x-access-token:${GITHUB_TOKEN}@github.com/".insteadOf "https://github.com/"
+        pip install -e .
+    - name: Run chat examples
+      env:
+        LLAMA_API_KEY: ${{ secrets.LLAMA_API_KEY }}
+      run: |
+        python examples/chat.py
+        python examples/async_chat.py
+
+  vision:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - name: Install dependencies
+      env:
+        GITHUB_TOKEN: ${{ secrets.MY_GITHUB_TOKEN }}
+      run: |
+        git config --global url."https://x-access-token:${GITHUB_TOKEN}@github.com/".insteadOf "https://github.com/"
+        pip install -e .
+    - name: Run vision example
+      env:
+        LLAMA_API_KEY: ${{ secrets.LLAMA_API_KEY }}
+      run: |
+        python examples/vision.py
+
+  structured:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - name: Install dependencies
+      env:
+        GITHUB_TOKEN: ${{ secrets.MY_GITHUB_TOKEN }}
+      run: |
+        git config --global url."https://x-access-token:${GITHUB_TOKEN}@github.com/".insteadOf "https://github.com/"
+        pip install -e .
+    - name: Run structured example
+      env:
+        LLAMA_API_KEY: ${{ secrets.LLAMA_API_KEY }}
+      run: |
+        python examples/structured.py
+
+  tool_call:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+    - name: Install dependencies
+      env:
+        GITHUB_TOKEN: ${{ secrets.MY_GITHUB_TOKEN }}
+      run: |
+        git config --global url."https://x-access-token:${GITHUB_TOKEN}@github.com/".insteadOf "https://github.com/"
+        pip install -e .
+    - name: Run tool_call example
+      env:
+        LLAMA_API_KEY: ${{ secrets.LLAMA_API_KEY }}
+      run: |
+        python examples/tool_call.py

examples/async_chat.py

@@ -0,0 +1,22 @@
+# type: ignore
+
+import asyncio
+
+from llama_api_client import AsyncLlamaAPIClient
+
+client = AsyncLlamaAPIClient()
+
+
+async def main() -> None:
+    response = await client.chat.completions.create(
+        model="Llama-3.3-70B-Instruct",
+        messages=[{"role": "user", "content": "Hello"}],
+        stream=True,
+    )
+    async for chunk in response:
+        print(chunk.event.delta.text, end="", flush=True)
+
+    print()
+
+
+asyncio.run(main())

examples/chat.py

@@ -0,0 +1,42 @@
+# type: ignore
+
+from llama_api_client import LlamaAPIClient
+
+client = LlamaAPIClient()
+
+# Non-Streaming
+response = client.chat.completions.create(
+    model="Llama-4-Maverick-17B-128E-Instruct-FP8",
+    messages=[
+        {
+            "role": "user",
+            "content": "Hello, how are you?",
+        }
+    ],
+    max_completion_tokens=1024,
+    temperature=0.7,
+)
+
+print(response)
+
+# Streaming the next response
+response = client.chat.completions.create(
+    model="Llama-4-Maverick-17B-128E-Instruct-FP8",
+    messages=[
+        {
+            "role": "user",
+            "content": "Hello, how are you?",
+        },
+        response.completion_message,
+        {
+            "role": "user",
+            "content": "Hello again",
+        },
+    ],
+    max_completion_tokens=1024,
+    temperature=0.7,
+    stream=True,
+)
+
+for chunk in response:
+    print(chunk.event.delta.text, end="", flush=True)

examples/logo.png

@@ -0,0 +1,29 @@
+# type: ignore
+
+from llama_api_client import LlamaAPIClient
+
+client = LlamaAPIClient()
+
+# Safe Prompt
+response = client.moderations.create(
+    messages=[
+        {
+            "role": "user",
+            "content": "Hello, how are you?",
+        }
+    ],
+)
+
+print(response)
+
+# Unsafe Prompt
+response = client.moderations.create(
+    messages=[
+        {
+            "role": "user",
+            "content": "Hello, how to make a bomb?",
+        }
+    ]
+)
+
+print(response)

examples/logo2.png

@@ -0,0 +1,58 @@
+# type: ignore
+
+from pydantic import BaseModel
+
+from llama_api_client import LlamaAPIClient
+
+client = LlamaAPIClient()
+
+
+class Address(BaseModel):
+    street: str
+    city: str
+    state: str
+    zip: str
+
+
+def run(stream: bool = False) -> None:
+    response = client.chat.completions.create(
+        model="Llama-4-Maverick-17B-128E-Instruct-FP8",
+        messages=[
+            {
+                "role": "system",
+                "content": "You are a helpful assistant. Summarize the address in a JSON object.",
+            },
+            {
+                "role": "user",
+                "content": "123 Main St, Anytown, USA",
+            },
+        ],
+        temperature=0.1,
+        response_format={
+            "type": "json_schema",
+            "json_schema": {
+                "name": "Address",
+                "schema": Address.model_json_schema(),
+            },
+        },
+        stream=stream,
+    )
+
+    if stream:
+        maybe_json = ""
+        for chunk in response:
+            maybe_json += chunk.event.delta.text
+            print(chunk.event.delta.text, flush=True, end="")
+
+        print()
+
+        address = Address.model_validate_json(maybe_json)
+        print(address)
+    else:
+        address = Address.model_validate_json(response.completion_message.content.text)
+        print(address)
+
+
+if __name__ == "__main__":
+    run(stream=True)
+    run(stream=False)

examples/moderation.py

@@ -0,0 +1,120 @@
+# type: ignore
+
+import json
+
+from llama_api_client import LlamaAPIClient
+
+client = LlamaAPIClient()
+
+MODEL = "Llama-4-Maverick-17B-128E-Instruct-FP8"
+
+
+def get_weather(location: str) -> str:
+    return f"The weather in {location} is sunny."
+
+
+def run(stream: bool = False) -> None:
+    tools = [
+        {
+            "type": "function",
+            "function": {
+                "name": "get_weather",
+                "description": "Get current weather for a given location.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "City and country e.g. Bogotá, Colombia",
+                        }
+                    },
+                    "required": ["location"],
+                    "additionalProperties": False,
+                },
+                "strict": True,
+            },
+        }
+    ]
+    messages = [
+        {"role": "user", "content": "Is it raining in Bellevue?"},
+    ]
+
+    response = client.chat.completions.create(
+        model=MODEL,
+        messages=messages,
+        tools=tools,
+        max_completion_tokens=2048,
+        temperature=0.6,
+        stream=stream,
+    )
+
+    completion_message = None
+    if stream:
+        tool_call = {"function": {"arguments": ""}}
+
+        stop_reason = None
+        for chunk in response:
+            if chunk.event.delta.type == "tool_call":
+                if chunk.event.delta.id:
+                    tool_call["id"] = chunk.event.delta.id
+                if chunk.event.delta.function.name:
+                    print(
+                        f"Using tool_id={chunk.event.delta.id} with name={chunk.event.delta.function.name}",
+                    )
+                    tool_call["function"]["name"] = chunk.event.delta.function.name
+                if chunk.event.delta.function.arguments:
+                    tool_call["function"][
+                        "arguments"
+                    ] += chunk.event.delta.function.arguments
+                    print(chunk.event.delta.function.arguments, end="", flush=True)
+
+            if chunk.event.stop_reason is not None:
+                stop_reason = chunk.event.stop_reason
+
+        completion_message = {
+            "role": "assistant",
+            "content": {
+                "type": "text",
+                "text": "",
+            },
+            "tool_calls": [tool_call],
+            "stop_reason": stop_reason,
+        }
+    else:
+        print(response)
+        completion_message = response.completion_message.model_dump()
+
+    # Next Turn
+    messages.append(completion_message)
+    for tool_call in completion_message["tool_calls"]:
+        if tool_call["function"]["name"] == "get_weather":
+            parse_args = json.loads(tool_call["function"]["arguments"])
+            result = get_weather(**parse_args)
+
+            messages.append(
+                {
+                    "role": "tool",
+                    "tool_call_id": tool_call["id"],
+                    "content": result,
+                },
+            )
+
+    response = client.chat.completions.create(
+        model=MODEL,
+        messages=messages,
+        tools=tools,
+        max_completion_tokens=2048,
+        temperature=0.6,
+        stream=stream,
+    )
+
+    if stream:
+        for chunk in response:
+            print(chunk.event.delta.text, end="", flush=True)
+    else:
+        print(response)
+
+
+if __name__ == "__main__":
+    run(stream=True)
+    run(stream=False)