idontcalculate

from config import COLLECTION_NAME
import os
import csv
from qdrant_client.http.models import VectorParams, PointStruct
from dotenv import load_dotenv
from generate_embedding import get_book_vector
from connect_qdrant import get_qdrant_client

load_dotenv()
qdrant_client = get_qdrant_client()

idontcalculate

from fastembed.embedding import TextEmbedding

def get_book_vector(book_data):
    embedder = TextEmbedding(model_name="BAAI/bge-base-en")
    text = f"{book_data['title']} {book_data['description']}"
    vector = list(embedder.embed(text))
    return vector[0]  # Since embed returns a generator, we convert it to a list and take the first item.

def get_query_vector(query_text):
    embedder = TextEmbedding(model_name="BAAI/bge-base-en")

idontcalculate

from qdrant_client import QdrantClient
from qdrant_client.http.models import Distance, VectorParams
from config import QDRANT_API_KEY, QDRANT_URL

def get_qdrant_client():
    qdrant_client = QdrantClient(
        url=QDRANT_URL,
        api_key=QDRANT_API_KEY,
    )
    # Ensure the collection exists

idontcalculate

import tensorflow as tf
from tensorflow.keras.models import load_model
import gradio as gr
import numpy as np
from PIL import Image

# Load the saved model
model = load_model("modelVGG16.h5")

# Define the prediction function

idontcalculate

import tensorflow as tf
from tensorflow.keras.applications import VGG16
from tensorflow.keras import layers, models, optimizers
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.callbacks import EarlyStopping

# Load the pre-trained VGG16 model without the top layer
base_model = VGG16(input_shape=(256, 256, 3), include_top=False, weights='imagenet')

# Freeze the convolutional base

idontcalculate

from tensorflow.keras.applications import VGG16
from tensorflow.keras import layers, models
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.losses import BinaryCrossentropy
from tensorflow.keras.metrics import BinaryAccuracy

# Load the pre-trained VGG16 model without the top layer
pretrained = VGG16(input_shape=(256, 256, 3), include_top=False, weights="imagenet")
pretrained.trainable = False

idontcalculate

from llama_index.agent import FnRetrieverOpenAIAgent
from llama_index.llms import OpenAI

# Initialize the LLM
llm = OpenAI(model="gpt-3.5-turbo-0613")

# Initialize the FnRetrieverOpenAIAgent
top_agent = FnRetrieverOpenAIAgent.from_retriever(
   obj_index.as_retriever(similarity_top_k=4),
   system_prompt=""" \

idontcalculate

# Create vector_index instance
vector_index = VectorStoreIndex(nodes, service_context=service_context)

# Build the summary index
summary_index = SummaryIndex(nodes, service_context=service_context)

# Now you can safely define query engines since vector_index is defined
vector_query_engine = vector_index.as_query_engine()
summary_query_engine = summary_index.as_query_engine()

idontcalculate

from llama_index.agent import OpenAIAgent
from llama_index import load_index_from_storage, StorageContext
from llama_index.node_parser import SentenceSplitter

# Initialize the SentenceSplitter node parser
node_parser = SentenceSplitter()

#load documents and build vector index
for idx, patent_title in enumerate(patent_titles):
    file_path = os.path.join(patents_dir, f"{patent_title}.txt")

idontcalculate

query_engine_tools = [
    QueryEngineTool(
        query_engine=tesla_engine,
        metadata=ToolMetadata(
            name="tesla_tool",
            description=(
                "Provides information about Teslas predictions for future "
                "Use a detailed plain text question as input to the tool."
            ),
        ),