File size: 1,440 Bytes
6ca31d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.core import Settings
from qdrant_client import QdrantClient
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core import StorageContext
from llama_index.vector_stores.qdrant import QdrantVectorStore
from llama_cloud_services import LlamaParse
from typing import List
import os


qdrant_client = QdrantClient(url=os.getenv("qdrant_url"), api_key=os.getenv("qdrant_api_key"))
embedder = HuggingFaceEmbedding(model_name="nomic-ai/modernbert-embed-base", device="cpu")
Settings.embed_model = embedder

def ingest_documents(files: List[str], collection_name: str, llamaparse: True, llamacloud_api_key: str):
    vector_store = QdrantVectorStore(client=qdrant_client, collection_name=collection_name, enable_hybrid=True)
    storage_context = StorageContext.from_defaults(vector_store=vector_store)
    if llamaparse: 
        parser = LlamaParse(
            result_type="markdown",
            api_key=llamacloud_api_key
        )
        file_extractor = {".pdf": parser}
        documents = SimpleDirectoryReader(input_files=files, file_extractor=file_extractor).load_data()
    else:
        documents = SimpleDirectoryReader(input_files=files).load_data()
    index = VectorStoreIndex.from_documents(
        documents,
        storage_context=storage_context,
    )
    return index