llama.cpp/examples/server_embd.py
compilade 3fd62a6b1c
py : type-check all Python scripts with Pyright (#8341)
* py : type-check all Python scripts with Pyright

* server-tests : use trailing slash in openai base_url

* server-tests : add more type annotations

* server-tests : strip "chat" from base_url in oai_chat_completions

* server-tests : model metadata is a dict

* ci : disable pip cache in type-check workflow

The cache is not shared between branches, and it's 250MB in size,
so it would become quite a big part of the 10GB cache limit of the repo.

* py : fix new type errors from master branch

* tests : fix test-tokenizer-random.py

Apparently, gcc applies optimisations even when pre-processing,
which confuses pycparser.

* ci : only show warnings and errors in python type-check

The "information" level otherwise has entries
from 'examples/pydantic_models_to_grammar.py',
which could be confusing for someone trying to figure out what failed,
considering that these messages can safely be ignored
even though they look like errors.
2024-07-07 15:04:39 -04:00

36 lines
971 B
Python

import asyncio
import asyncio.threads
import requests
import numpy as np
n = 8
result = []
async def requests_post_async(*args, **kwargs):
return await asyncio.threads.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}")