Skip to content

LLMstudio Version 1.0.6: langraph integration #217

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Apr 24, 2025
Merged

LLMstudio Version 1.0.6: langraph integration #217

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
5376b23
Feature/langraph integration (#215)
diogoncalves Apr 22, 2025
82c4f9e
[fix] bump prerelease version in pyproject.toml
actions-user Apr 22, 2025
7fd58a3
[fix] bump prerelease version in pyproject.toml
actions-user Apr 22, 2025
71c050f
Update core.py
diogoncalves Apr 23, 2025
ce0461c
Update core.py
diogoncalves Apr 23, 2025
54c2da4
Update core.py
diogoncalves Apr 23, 2025
02c06f5
Update core.py
diogoncalves Apr 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 24 additions & 12 deletions examples/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,13 @@
from dotenv import load_dotenv
load_dotenv()

def run_provider(provider, model, api_key=None, **kwargs):
def run_provider(provider, model, api_key=None=None, **kwargs):
print(f"\n\n###RUNNING for <{provider}>, <{model}> ###")
print(f"\n\n###RUNNING for <{provider}>, <{model}> ###")
llm = LLMCore(provider=provider, api_key=api_key, **kwargs)

latencies = {}
latencies = {}

print("\nAsync Non-Stream")
chat_request = build_chat_request(model, chat_input="Hello, my name is Jason", is_stream=False)
string = """
Expand Down Expand Up @@ -49,14 +51,19 @@ def run_provider(provider, model, api_key=None, **kwargs):
"""
#chat_request = build_chat_request(model, chat_input=string, is_stream=False)


response_async = asyncio.run(llm.achat(**chat_request))
pprint(response_async)
latencies["async (ms)"]= response_async.metrics["latency_s"]*1000


print("\nAsync Stream")


print("\nAsync Stream")
async def async_stream():
chat_request = build_chat_request(model, chat_input="Hello, my name is Tom", is_stream=True)
chat_request = build_chat_request(model, chat_input="Hello, my name is Tom", is_stream=True)

response_async = await llm.achat(**chat_request)
async for p in response_async:
Expand All @@ -71,6 +78,8 @@ async def async_stream():
asyncio.run(async_stream())


print("\nSync Non-Stream")
chat_request = build_chat_request(model, chat_input="Hello, my name is Alice", is_stream=False)
print("\nSync Non-Stream")
chat_request = build_chat_request(model, chat_input="Hello, my name is Alice", is_stream=False)

Expand All @@ -81,7 +90,6 @@ async def async_stream():

print("\nSync Stream")
chat_request = build_chat_request(model, chat_input="Hello, my name is Mary", is_stream=True)


response_sync_stream = llm.chat(**chat_request)
for p in response_sync_stream:
Expand All @@ -96,6 +104,7 @@ async def async_stream():
return latencies

def build_chat_request(model: str, chat_input: str, is_stream: bool, max_tokens: int=1000):
if model.startswith(('o1', 'o3')):
if model.startswith(('o1', 'o3')):
chat_request = {
"chat_input": chat_input,
Expand All @@ -116,6 +125,16 @@ def build_chat_request(model: str, chat_input: str, is_stream: bool, max_tokens:
"maxTokens": max_tokens
}
}
elif 'amazon.nova' in model or 'anthropic.claude' in model:
chat_request = {
"chat_input": chat_input,
"model": model,
"is_stream": is_stream,
"retries": 0,
"parameters": {
"maxTokens": max_tokens
}
}
else:
chat_request = {
"chat_input": chat_input,
Expand All @@ -135,19 +154,13 @@ def multiple_provider_runs(provider:str, model:str, num_runs:int, api_key:str, *
for _ in range(num_runs):
latencies = run_provider(provider=provider, model=model, api_key=api_key, **kwargs)
pprint(latencies)



def run_chat_all_providers():
# OpenAI
multiple_provider_runs(provider="openai", model="gpt-4o-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
multiple_provider_runs(provider="openai", model="o3-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
#multiple_provider_runs(provider="openai", model="o1-preview", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)

# Azure
multiple_provider_runs(provider="azure", model="gpt-4o-mini", num_runs=1, api_key=os.environ["AZURE_API_KEY"], api_version=os.environ["AZURE_API_VERSION"], api_endpoint=os.environ["AZURE_API_ENDPOINT"])
#multiple_provider_runs(provider="azure", model="gpt-4o", num_runs=1, api_key=os.environ["AZURE_API_KEY"], api_version=os.environ["AZURE_API_VERSION"], api_endpoint=os.environ["AZURE_API_ENDPOINT"])
#multiple_provider_runs(provider="azure", model="o1-mini", num_runs=1, api_key=os.environ["AZURE_API_KEY"], api_version=os.environ["AZURE_API_VERSION"], api_endpoint=os.environ["AZURE_API_ENDPOINT"])
#multiple_provider_runs(provider="azure", model="o1-preview", num_runs=1, api_key=os.environ["AZURE_API_KEY"], api_version=os.environ["AZURE_API_VERSION"], api_endpoint=os.environ["AZURE_API_ENDPOINT"])

# Azure
multiple_provider_runs(provider="azure", model="gpt-4o-mini", num_runs=1, api_key=os.environ["AZURE_API_KEY"], api_version=os.environ["AZURE_API_VERSION"], api_endpoint=os.environ["AZURE_API_ENDPOINT"])
Expand All @@ -156,7 +169,6 @@ def run_chat_all_providers():
#multiple_provider_runs(provider="azure", model="o1-preview", num_runs=1, api_key=os.environ["AZURE_API_KEY"], api_version=os.environ["AZURE_API_VERSION"], api_endpoint=os.environ["AZURE_API_ENDPOINT"])



#multiple_provider_runs(provider="anthropic", model="claude-3-opus-20240229", num_runs=1, api_key=os.environ["ANTHROPIC_API_KEY"])

#multiple_provider_runs(provider="azure", model="o1-preview", num_runs=1, api_key=os.environ["AZURE_API_KEY"], api_version=os.environ["AZURE_API_VERSION"], api_endpoint=os.environ["AZURE_API_ENDPOINT"])
Expand Down Expand Up @@ -214,4 +226,4 @@ def run_send_imgs():
# if p.metrics:
# p.clean_print()

run_send_imgs()
run_send_imgs()
Loading