from haystack import Pipeline, Document
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.writers import DocumentWriter
from haystack.components.embedders import SentenceTransformersDocumentEmbedder
from haystack.components.generators import OpenAIGenerator
from haystack.utils import Secret
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.components.builders import PromptBuilder
from haystack.components.embedders import SentenceTransformersTextEmbedder
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
from haystack.dataclasses import ChatMessage
import pandas as pd

# Load product data from CSV
df = pd.read_csv("product_sample.csv")

# Initialize an in-memory document store
document_store = InMemoryDocumentStore()

# Convert the product data into Haystack Document objects
documents = [
    Document(
        content=item.product_name, 
        meta={
            "id": item.uniq_id, 
            "price": item.selling_price, 
            "url": item.product_url
        }
    ) for item in df.itertuples()
]

# Create a pipeline for indexing the documents
indexing_pipeline = Pipeline()

# Add a document embedder to the pipeline using Sentence Transformers model
indexing_pipeline.add_component(
    instance=SentenceTransformersDocumentEmbedder(model="sentence-transformers/all-MiniLM-L6-v2"), name="doc_embedder"
)

# Add a document writer to the pipeline to store documents in the document store
indexing_pipeline.add_component(instance=DocumentWriter(document_store=document_store), name="doc_writer")

# Connect the embedder's output to the writer's input
indexing_pipeline.connect("doc_embedder.documents", "doc_writer.documents")

# Run the indexing pipeline to process and store the documents
indexing_pipeline.run({"doc_embedder": {"documents": documents}})