mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 02:44:36 +00:00
34 lines
939 B
Python
34 lines
939 B
Python
import asyncio
|
|
import requests
|
|
import numpy as np
|
|
|
|
n = 8
|
|
|
|
result = []
|
|
|
|
async def requests_post_async(*args, **kwargs):
|
|
return await asyncio.to_thread(requests.post, *args, **kwargs)
|
|
|
|
async def main():
|
|
model_url = "http://127.0.0.1:6900"
|
|
responses: list[requests.Response] = await asyncio.gather(*[requests_post_async(
|
|
url= f"{model_url}/embedding",
|
|
json= {"content": str(0)*1024}
|
|
) for i in range(n)])
|
|
|
|
for response in responses:
|
|
embedding = response.json()["embedding"]
|
|
print(embedding[-8:])
|
|
result.append(embedding)
|
|
|
|
asyncio.run(main())
|
|
|
|
# compute cosine similarity
|
|
|
|
for i in range(n-1):
|
|
for j in range(i+1, n):
|
|
embedding1 = np.array(result[i])
|
|
embedding2 = np.array(result[j])
|
|
similarity = np.dot(embedding1, embedding2) / (np.linalg.norm(embedding1) * np.linalg.norm(embedding2))
|
|
print(f"Similarity between {i} and {j}: {similarity:.2f}")
|