app/run.py

# This script inits the models and adds an example collection to the Vectorstore
# %%
import os
import pathlib

from load_model import load_embedding
from utils import get_chroma_client
from load_vectors import load_from_web, create_and_add, load_and_split

current_path = str( pathlib.Path(__file__).parent.resolve() )
with open(current_path+'/.openaiapikey', 'r') as reader:
    os.environ['OPENAI_API_KEY']=reader.read()
import load_model

# %%
#load_model.load_gpu_model("decapoda-research/llama-7b-hf") #Download local model
llm= load_model.load_openai_model()

# %% 
#Load example Data
client = get_chroma_client()
client.reset()
ef = load_embedding("hkunlp/instructor-large")
collection_name="axaterms"
metadata= {"loaded_docs":[], "Subject":"AXA Terms", "model_name": ef.model_name}
selected_collection = client.create_collection(collection_name, embedding_function=ef, metadata=metadata) 

docs_tarifs= [
    "https://www.axa.de/site/axa-de/get/documents_E1805589786/axade/medien/privatkunden/fahrzeugversicherungen/kfz-versicherung/start-and-drive/start-and-drive-versicherungsbedingungen.pdf",
    "https://www.axa.de/site/axa-de/get/documents_E-298610932/axade/medien/privatkunden/haftpflicht-und-recht/rechtsschutz/versicherungsbedingungen-roland-rechtsschutz.pdf",
    "https://www.axa.de/site/axa-de/get/documents_E1450059874/axade/medien/privatkunden/haftpflicht-und-recht/private%20haftpflichtversicherung/privathaftpflicht-versicherungsbedingungen-leistungspaket-L.pdf",
    "https://www.axa.de/site/axa-de/get/documents_E1883536226/axade/medien/privatkunden/haus-und-wohnen/hausratversicherung/hausrat-versicherungsbedingungen-L.pdf",
]

# %%
# Load collection to get metadata
loaded_collection = client.get_collection(collection_name)
model_name = loaded_collection.metadata['model_name']

# %%

docs = load_from_web(docs_tarifs)
sub_docs = load_and_split(docs, chunk_size=1000)
create_and_add(collection_name, sub_docs, model_name, metadata)

# %%
chain = load_model.create_chain(llm, collection=collection_name, model_name=model_name)
#result = chain({"query": "Ist mein Kinderwagen bei einem Leitungswasserschaden mitversichert?"})
#print(result)