File size: 1,962 Bytes
83f1514 |
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 |
from openai import OpenAI
from src.nlp.data.test_texts import TEXTS
class ModelName:
DEEP_SEEK_R1 = "deepseek/deepseek-r1:free"
DEEP_SEEK_R1_DISTILL_LLAMA = "deepseek/deepseek-r1-distill-llama-70b:free"
QWEN_CODER_INSTRUCT = "qwen/qwen-2.5-coder-32b-instruct:free"
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="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",
)
def deep_seek_extraction(text, model_name: str):
return client.chat.completions.create(
extra_headers={
# "HTTP-Referer": "<YOUR_SITE_URL>", # Optional. Site URL for rankings on openrouter.ai.
# "X-Title": "<YOUR_SITE_NAME>", # Optional. Site title for rankings on openrouter.ai.
},
extra_body={},
model=model_name,
messages=[
{
"role": "user",
"content": """
Extrahiere die Veranstaltungsdaten (wenn vorhanden) aus dem Text in folgendem JSON Format:
{
"title": String,
"start_date": String,
"end_date": String | None,
"start_time": String | None,
"end_time": String | None,
"admittance_time": String | None,
"location_name": String | None,
"adress": {
"street": String | None,
"housenumber": String | None,
"postal_code": String | None,
"city": String | None,
}
"categories": Array<String> | None,
"organizers": Array<String> | None,
}
Text:
"""
+ text
}
]
)
for text in TEXTS:
print("*"*100)
print("TEXT")
print(text)
completion = deep_seek_extraction(text, ModelName.QWEN_CODER_INSTRUCT)
print("DATA:")
print(completion.choices[0].message.content)
print("*"*100)
|