File size: 1,252 Bytes
91bee69
 
d92c861
3a02c2a
07fb065
 
 
 
 
 
 
 
 
 
 
 
 
572cc27
d92c861
 
 
 
 
 
 
 
 
66e97f3
07fb065
aaf0100
 
07fb065
 
 
 
 
 
 
 
 
 
 
 
 
aaf0100
 
 
91bee69
3a02c2a
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
from fastapi import FastAPI, HTTPException
from fastapi.responses import JSONResponse
from fastapi.middleware.cors import CORSMiddleware

from transformers import AutoModel, AutoTokenizer
import torch

device = torch.device("cpu")

# Load the model and tokenizer
model = AutoModel.from_pretrained(
    "nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True
)


app = FastAPI()
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)


@app.post("/get_embeding")
async def get_embeding(chunk):

        # Tokenize the input text
        inputs = tokenizer(chunk, return_tensors="pt")
    
        # Generate embeddings
        with torch.no_grad():
            outputs = model(**inputs)
    
        # The embeddings can be found in the 'last_hidden_state'
        embeddings = outputs.last_hidden_state
    
        # Optionally, you can average the token embeddings to get a single vector for the sentence
        sentence_embedding = torch.mean(embeddings, dim=1)
    
        #print(sentence_embedding)
        return sentence_embedding.tolist()