b54c2def30
- Add database migrations (006-028) for face recognition, identity, file_uuid - Add test scripts for ASR, face, search, processing - Add portal frontend (Tauri) - Add config, benchmark, and monitoring utilities - Add model checkpoints and pretrained model references
57 lines
1.9 KiB
Python
57 lines
1.9 KiB
Python
import json
|
|
import requests
|
|
import sys
|
|
|
|
|
|
def get_embedding(text, prefix="search_query: "):
|
|
url = "http://localhost:11434/api/embeddings"
|
|
payload = {"model": "nomic-embed-text-v2-moe:latest", "prompt": f"{prefix}{text}"}
|
|
response = requests.post(url, json=payload)
|
|
if response.status_code != 200:
|
|
print(f"Error: {response.status_code} - {response.text}")
|
|
return None
|
|
data = response.json()
|
|
return data["embedding"]
|
|
|
|
|
|
def search_qdrant(vector, limit=10):
|
|
url = "http://127.0.0.1:6333/collections/momentry_rule1/points/search"
|
|
headers = {
|
|
"Content-Type": "application/json",
|
|
"api-key": "Test3200Test3200Test3200",
|
|
}
|
|
payload = {"vector": vector, "limit": limit, "with_payload": True}
|
|
response = requests.post(url, json=payload, headers=headers)
|
|
if response.status_code != 200:
|
|
print(f"Qdrant error: {response.status_code} - {response.text}")
|
|
return None
|
|
return response.json()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
# Test Chinese text
|
|
text = "檔案傳輸"
|
|
print(f"Testing embedding for: '{text}'")
|
|
vector = get_embedding(text)
|
|
if vector:
|
|
print(f"Vector length: {len(vector)}")
|
|
print(f"First 5 values: {vector[:5]}")
|
|
|
|
# Search Qdrant
|
|
print("\nSearching Qdrant...")
|
|
results = search_qdrant(vector, limit=5)
|
|
if results:
|
|
print(f"Found {len(results['result'])} results")
|
|
for i, r in enumerate(results["result"]):
|
|
payload = r.get("payload", {})
|
|
text = payload.get("text", "No text")
|
|
chunk_id = payload.get("chunk_id", "N/A")
|
|
uuid = payload.get("uuid", "N/A")
|
|
score = r.get("score", 0)
|
|
print(f"{i + 1}. Score: {score:.4f}, UUID: {uuid}, Chunk: {chunk_id}")
|
|
print(f" Text: {text[:100]}...")
|
|
else:
|
|
print("No results")
|
|
else:
|
|
print("Failed to get embedding")
|