Spaces:
Sleeping
Sleeping
| import requests | |
| import sys | |
| import spacy | |
| from io import BytesIO | |
| import pandas as pd | |
| import json | |
| # Load your custom NER model | |
| nlp_ner = spacy.load("ner_model_v1") | |
| # def send_results_to_api(data, result_url): | |
| # headers = {"Content-Type": "application/json"} | |
| # response = requests.post(result_url, json=data, headers=headers) | |
| # if response.status_code == 200: | |
| # return response.json() # Return any response from the API if needed | |
| # else: | |
| # return {"error": f"Failed to send results to API: {response.status_code}"} | |
| def process_xlsx(params): | |
| # xlsx_file = 'https://fragilestatesindex.org/wp-content/uploads/2023/06/FSI-2023-DOWNLOAD.xlsx' | |
| try: | |
| params = json.loads(params) | |
| except json.JSONDecodeError as e: | |
| return {"error": f"Invalid JSON input: {e.msg} at line {e.lineno} column {e.colno}"} | |
| print(f"JSON : \n{params}") | |
| addresses = params.get("urls", []) | |
| if not params.get("normalfileID",[]): | |
| file_ids = [None]*len(addresses) | |
| else: | |
| file_ids = params.get("normalfileID",[]) | |
| # api = params.get("api", "") | |
| # job_id = params.get("job_id", "") | |
| solutions=[] | |
| text_id = 1 | |
| for adress,file_id in zip(addresses, file_ids): | |
| doc = nlp_ner(adress) | |
| # Initialize the dictionary to store the results | |
| entities_dict = {} | |
| # Extract entities and their indices | |
| for idx, ent in enumerate(doc.ents): | |
| if ent.label_ not in entities_dict: | |
| entities_dict[ent.label_] = [] | |
| entities_dict[ent.label_].append({'word': ent.text, 'index': idx}) | |
| # Create the final output dictionary | |
| # | |
| obj = {"text": adress, "answer":entities_dict, "qcUser": None, "normalfileID": file_id} | |
| solutions.append(obj) | |
| print(f"{text_id}/{len(addresses)}\n") | |
| text_id = text_id+1 | |
| # result_url = f"{api}/{job_id}" | |
| # send_results_to_api(solutions, result_url) | |
| return json.dumps({"solutions": solutions}) | |
| import gradio as gr | |
| inputt = gr.Textbox(label="Parameters (JSON format) Eg. {'texts':['file1.mp3','file2.wav']}") | |
| outputs = gr.JSON() | |
| application = gr.Interface(fn=process_xlsx, inputs=inputt, outputs=outputs, title="Named Entity Recognition with API Integration") | |
| application.launch() |