do_load = True
from qdrant_client import QdrantClient
from qdrant_client.models import Filter, FieldCondition, Range, MatchText
from datetime import datetime, timedelta
import numpy as np
import traceback
from bottle import route, run, template, request, debug
import open_clip
import torch
# %%
if do_load:
    model_name = 'ViT-SO400M-14-SigLIP-384'
    pretrained_name = 'webli'

    model, _, preprocess = open_clip.create_model_and_transforms(model_name, pretrained=pretrained_name)
    device = 'cpu'
    model.eval()
    tokenizer = open_clip.get_tokenizer(model_name)

TIMEOUT=2
# %%

collection_name = "nuggets_so400m"
client = QdrantClient(host="localhost", grpc_port=6334, prefer_grpc=True, timeout=TIMEOUT)
# %%
from bottle import route, run, template

@route('/get_text_match')
def get_matches():
    valid_cameras = {'sidefeeder','ptz','railing','hummingbird','pond'}
    query = request.query.get('query','A large bird eating corn')
    cameras = request.query.get('cameras','sidefeeder')
    cams = set(cameras.split(',')).intersection(valid_cameras)

    max_age = int(request.query.get('age',5));
    print({'Cameras':cams,'Max Age':max_age,'Query':query})
# %%
    max_date = datetime.now()
    min_date = max_date - timedelta(days=(max_age))

    days_step = (max_date- min_date).days
    date_arrays = list()
    for i in range(days_step):
        date_arrays.append(max_date - timedelta(days=i))
# %%
    string_filter = list()
    for cand_date in date_arrays:
        string_filter.append(cand_date.strftime('%Y/%m/%d'))


    should_list = list()
    if max_age == 0:
        string_filter=['']

    for str_filt in string_filter:
        for cam in cams:
            str_use = cam+'/'+str_filt
            print(str_use)
            ccond  = FieldCondition(key='filepath',match=MatchText(text=str_use))
            should_list.append(ccond)

            


    condition_dict = Filter(should = should_list)
    if len(should_list) == 0:
        return_this = {'query':query,'num_videos':0,'results':[]}
        return return_this

  
    averaged = False
    if isinstance(query, str):
        averaged = bool(averaged)
    
    num_videos = int(request.query.get('num_videos',5))

    if do_load:
        with torch.no_grad():
            text_tokenized = tokenizer(query)
            vec = model.encode_text(text_tokenized)
#            text_input = txt_processors['eval'](query)
#            sample = {'text_input':text_input}
#            vec = model.extract_features( sample)
            vec_search = vec.cpu().numpy().squeeze().tolist()
    else:
        sz_vec= client.get_collection(collection_name).config.params.vectors.size
        vec_search = np.random.random(sz_vec).tolist()



    if averaged:
        col_name=collection_name+'_averaged'
    else:
        col_name = collection_name

# %%
    try:
        error = ''
        if True:
            for i in range(num_videos, 100, 10):
                results = client.search(collection_name = col_name,
                                        query_vector = vec_search, limit=i, query_filter=condition_dict, timeout=TIMEOUT)
                num_video_got = len(set([x.payload['filepath'] for x in results]))
                if num_video_got >= num_videos:
                    break
        else:
            results = client.search(collection_name = col_name,
                                    query_vector = vec_search, limit=1, query_filter=condition_dict, timeout=TIMEOUT)
    except Exception as e:
        print(traceback.format_exc())
        error = traceback.format_exc()
        results = [];
  

    def linux_to_win_path(form):
        form = form.replace('/srv','file://192.168.1.242/thebears/Videos/merged/')
        return form

    def normalize_to_merged(path):
        path = path.replace('/srv/ftp','/mergedfs/ftp')
        path = path.replace('/mnt/archive2/videos/ftp','/mergedfs/ftp')
        return path

    resul = list()
    for x in results:
        pload =dict( x.payload)
        pload['filepath'] = normalize_to_merged(pload['filepath'])
        pload['score'] = x.score
        pload['winpath'] = linux_to_win_path(pload['filepath'])
        resul.append(pload)
# %%
    return_this = {'query':query,'num_videos':num_videos,'results':resul,'error':error}
    return return_this




debug(True)
run(host='0.0.0.0', port=53003, server='bjoern')