Skip to content

fix: load .env credentials in call_llm verification script #184

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

Open
payalkanyan wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: load .env credentials in call_llm verification script #184

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions utils/call_llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
import json
import requests
from datetime import datetime
import dotenv

# Configure logging
log_directory = os.getenv("LOG_DIR", "logs")
Expand Down Expand Up @@ -124,7 +125,7 @@ def _call_llm_provider(prompt: str) -> str:
except ValueError:
raise Exception(f"Failed to parse response as JSON from {provider}. The server might have returned an invalid response.")

# By default, we Google Gemini 2.5 pro, as it shows great performance for code understanding
# By default, we Google Gemini 1.5 flash, as it shows great performance for code understanding
def call_llm(prompt: str, use_cache: bool = True) -> str:
# Log the prompt
logger.info(f"PROMPT: {prompt}")
Expand Down Expand Up @@ -169,14 +170,15 @@ def _call_llm_gemini(prompt: str) -> str:
client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
else:
raise ValueError("Either GEMINI_PROJECT_ID or GEMINI_API_KEY must be set in the environment")
model = os.getenv("GEMINI_MODEL", "gemini-2.5-pro-exp-03-25")
model = os.getenv("GEMINI_MODEL", "gemini-1.5-flash")
response = client.models.generate_content(
model=model,
contents=[prompt]
)
return response.text

if __name__ == "__main__":
dotenv.load_dotenv()
test_prompt = "Hello, how are you?"

# First call - should hit the API
Expand Down