boladeE
859c17aad8
- Update config.py with Pinecone settings and model configurations - Implement VectorStore class with Pinecone backend - Add comprehensive vector operations (add, search, delete) - Set up proper error handling and metadata management - Add .gitignore for Python project
49 lines
1.2 KiB
Python
49 lines
1.2 KiB
Python
import requests
|
|
import json
|
|
|
|
def test_model(prompt):
|
|
"""Test the model with a simple prompt."""
|
|
url = "http://localhost:8000/direct-model"
|
|
|
|
payload = {
|
|
"prompt": prompt,
|
|
"max_length": 200,
|
|
"num_return_sequences": 1,
|
|
"temperature": 0.7,
|
|
"top_p": 0.9
|
|
}
|
|
|
|
print(f"Sending prompt: '{prompt}'")
|
|
|
|
try:
|
|
response = requests.post(url, json=payload)
|
|
|
|
if response.status_code == 200:
|
|
result = response.json()
|
|
print("\nGenerated text:")
|
|
print(result["generated_texts"][0])
|
|
else:
|
|
print(f"Error: {response.status_code}")
|
|
print(response.text)
|
|
except Exception as e:
|
|
print(f"Error: {str(e)}")
|
|
print("Make sure the FastAPI server is running on http://localhost:8000")
|
|
|
|
def main():
|
|
print("Simple LLM Test")
|
|
print("===============")
|
|
print("Enter your prompt (or 'quit' to exit):")
|
|
|
|
while True:
|
|
prompt = input("\n> ")
|
|
|
|
if prompt.lower() in ["quit", "exit", "q"]:
|
|
break
|
|
|
|
if not prompt.strip():
|
|
continue
|
|
|
|
test_model(prompt)
|
|
|
|
if __name__ == "__main__":
|
|
main() |