mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-03 09:22:01 +00:00
2002bc96bf
* server : refactoring (wip) * server : remove llava/clip objects from build * server : fix empty prompt handling + all slots idle logic * server : normalize id vars * server : code style * server : simplify model chat template validation * server : code style * server : minor * llama : llama_chat_apply_template support null buf * server : do not process embedding requests when disabled * server : reorganize structs and enums + naming fixes * server : merge oai.hpp in utils.hpp * server : refactor system prompt update at start * server : disable cached prompts with self-extend * server : do not process more than n_batch tokens per iter * server: tests: embeddings use a real embeddings model (#5908) * server, tests : bump batch to fit 1 embedding prompt * server: tests: embeddings fix build type Debug is randomly failing (#5911) * server: tests: embeddings, use different KV Cache size * server: tests: embeddings, fixed prompt do not exceed n_batch, increase embedding timeout, reduce number of concurrent embeddings * server: tests: embeddings, no need to wait for server idle as it can timout * server: refactor: clean up http code (#5912) * server : avoid n_available var ggml-ci * server: refactor: better http codes * server : simplify json parsing + add comment about t_last * server : rename server structs * server : allow to override FQDN in tests ggml-ci * server : add comments --------- Co-authored-by: Pierrick Hymbert <pierrick.hymbert@gmail.com>
35 lines
940 B
Python
35 lines
940 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}")
|
|
|