Spaces:
Running
Running
File size: 5,202 Bytes
9b70717 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
from openai import OpenAI
import os
import json
import re
from datetime import datetime
from utility.utils import log_response,LOG_TYPE_GPT
from groq import Groq
model = "llama3-70b-8192"
client = Groq(
api_key=os.environ.get("GROQ_API_KEY"),
)
log_directory = ".logs/gpt_logs"
prompt = """# Instructions
Given the following video script and timed captions, extract three visually concrete and specific keywords for each time segment that can be used to search for background videos. The keywords should be short and capture the main essence of the sentence. They can be synonyms or related terms. If a caption is vague or general, consider the next timed caption for more context. If a keyword is a single word, try to return a two-word keyword that is visually concrete. If a time frame contains two or more important pieces of information, divide it into shorter time frames with one keyword each. Ensure that the time periods are strictly consecutive and cover the entire length of the video. Each keyword should cover between 2-4 seconds. The output should be in JSON format, like this: [[[t1, t2], ["keyword1", "keyword2", "keyword3"]], [[t2, t3], ["keyword4", "keyword5", "keyword6"]], ...]. Please handle all edge cases, such as overlapping time segments, vague or general captions, and single-word keywords.
For example, if the caption is 'The cheetah is the fastest land animal, capable of running at speeds up to 75 mph', the keywords should include 'cheetah running', 'fastest animal', and '75 mph'. Similarly, for 'The Great Wall of China is one of the most iconic landmarks in the world', the keywords should be 'Great Wall of China', 'iconic landmark', and 'China landmark'.
Important Guidelines:
Use only English in your text queries.
Each search string must depict something visual.
The depictions have to be extremely visually concrete, like rainy street, or cat sleeping.
'emotional moment' <= BAD, because it doesn't depict something visually.
'crying child' <= GOOD, because it depicts something visual.
The list must always contain the most relevant and appropriate query searches.
['Car', 'Car driving', 'Car racing', 'Car parked'] <= BAD, because it's 4 strings.
['Fast car'] <= GOOD, because it's 1 string.
['Un chien', 'une voiture rapide', 'une maison rouge'] <= BAD, because the text query is NOT in English.
Note: Your response should be the response only and no extra text or data.
"""
def fix_json(json_str):
# Replace typographical apostrophes with straight quotes
json_str = json_str.replace("’", "'")
# Replace any incorrect quotes (e.g., mixed single and double quotes)
json_str = json_str.replace("“", "\"").replace("”", "\"").replace("‘", "\"").replace("’", "\"")
# Add escaping for quotes within the strings
json_str = json_str.replace('"you didn"t"', '"you didn\'t"')
return json_str
def getVideoSearchQueriesTimed(script,captions_timed):
end = captions_timed[-1][0][1]
try:
out = [[[0,0],""]]
while out[-1][0][1] != end:
content = call_OpenAI(script,captions_timed).replace("'",'"')
try:
out = json.loads(content)
except Exception as e:
print("content: \n", content, "\n\n")
print(e)
content = fix_json(content.replace("```json", "").replace("```", ""))
out = json.loads(content)
return out
except Exception as e:
print("error in response",e)
return None
def call_OpenAI(script,captions_timed):
user_content = """Script: {}
Timed Captions:{}
""".format(script,"".join(map(str,captions_timed)))
print("Content", user_content)
response = client.chat.completions.create(
model= model,
temperature=1,
messages=[
{"role": "system", "content": prompt},
{"role": "user", "content": user_content}
]
)
text = response.choices[0].message.content.strip()
text = re.sub('\s+', ' ', text)
print("Text", text)
log_response(LOG_TYPE_GPT,script,text)
return text
def merge_empty_intervals(segments):
if segments is None:
return []
merged = []
i = 0
while i < len(segments):
interval, url = segments[i]
if url is None:
# Find consecutive None intervals
j = i + 1
while j < len(segments) and segments[j][1] is None:
j += 1
# Merge consecutive None intervals with the previous valid URL
if i > 0:
prev_interval, prev_url = merged[-1]
if prev_url is not None and prev_interval[1] == interval[0]:
merged[-1] = [[prev_interval[0], segments[j-1][0][1]], prev_url]
else:
merged.append([interval, prev_url])
else:
merged.append([interval, None])
i = j
else:
merged.append([interval, url])
i += 1
return merged
|