Spaces:
Runtime error
Runtime error
File size: 3,741 Bytes
c2e327f 3545a80 c2e327f |
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 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
from sentence_transformers import SentenceTransformer, util
# from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
import time
import os
import json
import pandas as pd
import numpy as np
import category_encoders as ce
import string
import pickle
import tqdm.autonotebook
from fastapi import FastAPI, Request, UploadFile, File
from joblib import dump, load
from pydantic import BaseModel
import sys
from database_build import index_corpus
from predict_different_aas import ask_database
from predict_one_aas import query_specific_aas
from typing import Any, Dict, AnyStr, List, Union
import chromadb
from chromadb.config import Settings
from typing import Union
app = FastAPI(title="Interface Semantic Matching")
JSONObject = Dict[AnyStr, Any]
JSONArray = List[Any]
JSONStructure = Union[JSONArray, JSONObject]
class submodelElement(BaseModel):
datatype: str
definition: str
name: str
semantic_id: str
unit: str
return_matches: int
aas_id: str
number_aas_returned: int
@app.on_event("startup")
def load_hf_model():
global model
# Altes Modell
# model = SentenceTransformer('mboth/distil-eng-quora-sentence')
# Fine Tuned Modell
model = SentenceTransformer("gart-labor/eng-distilBERT-se-eclass")
# global model_translate
# model_translate = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")
# global tokenizer_translate
# tokenizer_translate = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")
with open("app/metadata.pickle", "rb") as handle:
global metalabel
metalabel = pickle.load(handle)
global client_chroma
client_chroma = chromadb.Client(
Settings(
chroma_api_impl="rest",
# chroma_server_host muss angepasst werden nach jedem Neustart AWS
chroma_server_host="3.67.86.197",
chroma_server_http_port=8000,
)
)
@app.post("/PostAssetAdministrationShellEmbeddings")
async def index_aas(aas: UploadFile = File(...)):
data = json.load(aas.file)
print(type(data))
# aas = new_file
#aas, submodels, conceptDescriptions, assets, aas_df, collection, aas_name= index_corpus(data, model, metalabel, client_chroma)
collection = index_corpus(data, model, metalabel, client_chroma)
ready = 'AAS ready'
return ready
@app.post("/GetSubmodelElementsFromDifferentAASBySemanticIdAndSemanticInformation")
def predict_different_aas(name: str, definition: str, number_aas_returned: Union[int, None] = 1, semantic_id: Union[str, None] = "NaN", unit: Union[str, None] = "NaN", datatype: Union[str, None] = "NaN"):
collections = client_chroma.list_collections()
query = {
"Name": name,
"Definition": definition,
"Unit": unit,
"Datatype": datatype,
"SemanticId": semantic_id,
"NumberAASReturned": number_aas_returned
}
results = ask_database(query, metalabel, model, collections, client_chroma)
return results
@app.post("/GetSubmodelElementsFromSpecificAASBySemanticIdAndSemanticInformation")
def predict_specific_aas(name: str, definition: str, aas_id: str, return_matches: Union[int, None] = 2, semantic_id: Union[str, None] = "NaN", unit: Union[str, None] = "NaN", datatype: Union[str, None] = "NaN"):
collections = client_chroma.list_collections()
query = {
"Name": name,
"Definition": definition,
"Unit": unit,
"Datatype": datatype,
"SemanticId": semantic_id,
"ReturnMatches": return_matches,
"AASId": aas_id,
}
result = query_specific_aas(query, metalabel, model, collections, client_chroma)
return result
|