目前，能提供大模型的厂商越来越多，比如OpenAI、Anthropic、Google、Deepseek、Qwen。
另外，也有很多开源大模型工具，比如Ollama、vLLM、ollama.cpp。
这里尝试探索对这些LLM访问进修融合集成的开源工具LiteLLM。
所用示例参考和修改自网络资料。
1 LiteLLM概要介绍
1.1 LiteLLM介绍
LiteLLM 是一个开源工具，它像一个大语言模型的"万能遥控器"。
LiteLLM提供标准的API 接口，用一套代码调用上百种不同厂商大模型。简化了集成管理的工作。
LiteLLM的核心价值在于将复杂的底层差异封装起来，为开发者提供统一、强大的管理能力。
LiteLLM通过模型名称区分大模型，比如
model="ollama/gemma3n:e2b"，表示模型为ollama大模型
model="openai/gemma3n:e2b"，表示模型为openai兼容的大模型
1.2 LiteLLM安装
LiteLLM可以通过pip快速安装，命令如下所示。
pip install litellm
2 同步访问示例
这里示例LiteLLM采用同步方式访问大模型。
2.1 Ollama接口示例
这里测试兼容ollama接口的大模型调用。
假设模型为gemma3n:e2b，则model="ollama/gemma3n:e2b"，示例代码如下。
from litellm import completion
response = completion(
model="ollama/gemma3n:e2b",
messages = [{ "content": "Hello, how are you?","role": "user"}],
api_base="http://localhost:11434"
)
print(response)输出示例如下所示
ModelResponse(id='chatcmpl-cadfb4cf-c6f1-4105-8fbf-094f3d44b579', created=1766390099, model='ollama/gemma3n:e2b', object='chat.completion', system_fingerprint=None, choices=Choices(finish_reason='stop', index=0, message=Message(content="Hello! I'm doing well, thank you for asking. As a large language model, I don't experience emotions like humans do, but I'm functioning optimally and ready to help. How are \*you\* doing today? 😊 \\n\\nIs there anything I can assist you with?\\n\\n\\n\\n", role='assistant', tool_calls=None, function_call=None, provider_specific_fields=None, reasoning_content=None)), usage=Usage(completion_tokens=62, prompt_tokens=21, total_tokens=83, completion_tokens_details=None, prompt_tokens_details=None))
2.2 Openai接口示例
这里测试兼容openai接口的大模型调用。
假设模型为gemma3n:e2b，则model="openai/gemma3n:e2b"，示例代码如下。
from litellm import completion
response = completion(
model="openai/gemma3n:e2b",
messages = [{ "content": "Hello, how are you?","role": "user"}],
api_base="http://localhost:11434/v1",
api_key="ollama"
)
print(response)输出如下所示
ModelResponse(id='chatcmpl-712', created=1766390462, model='gemma3n:e2b', object='chat.completion', system_fingerprint='fp_ollama', choices=Choices(finish_reason='stop', index=0, message=Message(content="Hello! I'm doing well, thank you for asking. As a large language model, I don't experience emotions or feelings like humans do, but I'm functioning optimally and ready to assist you. \\n\\nHow are \*you\* doing today? Is there anything I can help you with? 😊\\n\\n\\n\\n", role='assistant', tool_calls=None, function_call=None, provider_specific_fields={'refusal': None}), provider_specific_fields={}), usage=Usage(completion_tokens=65, prompt_tokens=15, total_tokens=80, completion_tokens_details=None, prompt_tokens_details=None), service_tier=None)
3 异步访问示例
这里示例LiteLLM采用同步方式访问大模型。
model等参数配置与同步访问一致，因为是异步访问，需要设置stream=True。
以下是流式访问openai接口兼容大模型的示例代码。
from litellm import completion
import os
response = completion(
model="openai/gemma3n:e2b",
messages=[{ "content": "Hello, how are you?","role": "user"}],
api_base="http://localhost:11434/v1",
api_key="ollama",
stream=True,
)
for item in response:
print(item)输出如下所示
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='I', role='assistant', function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' am', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' doing', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' well', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=',', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' thank', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' you', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' for', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' asking', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='!', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' As', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' a', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' large', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' language', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' model', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=',', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' I', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' don', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content="'", role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='t', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' experience', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' feelings', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' like', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' humans', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' do', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=',', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' but', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' I', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content="'", role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='m', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' functioning', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' optimally', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' and', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' ready', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' to', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' assist', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' you', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='.', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' ', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='\\n\\n', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='How', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' are', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' \*', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='you', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='\*', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' doing', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' today', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='?', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' Is', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' there', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' anything', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' I', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' can', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' help', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' you', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' with', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='?', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content=' 😊', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason=None, index=0, delta=Delta(provider_specific_fields=None, refusal=None, content='\\n\\n\\n\\n', role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None, citations=None, service_tier=None)
ModelResponseStream(id='chatcmpl-570', created=1766391486, model='gemma3n:e2b', object='chat.completion.chunk', system_fingerprint='fp_ollama', choices=StreamingChoices(finish_reason='stop', index=0, delta=Delta(provider_specific_fields=None, content=None, role=None, function_call=None, tool_calls=None, audio=None), logprobs=None), provider_specific_fields=None)
referrence
LiteLLM - Getting Started