def get_metadata(filename):
   for item in metadata:
    if item["url"] == filename:
     return item
   return {}
documents = SimpleDirectoryReader(dir_documents, file_metadata=get_metadata).load_data()
node_parser = SentenceWindowNodeParser.from_defaults(window_size=3,window_metadata_key="window",original_text_metadata_key="original_text")
nodes = node_parser.get_nodes_from_documents(documents)
transformations = [title_extractor, qa_extractor]
neo4j_vector_store = Neo4jVectorStore(neo_username, neo_password, neo_url, embed_dim, hybrid_search=True, index_name=index_name)
storage_context = StorageContext.from_defaults(vector_store=neo4j_vector_store)
vector_index = get_vector_index(neo_username, neo_password, neo_url, embed_dim, index_name)
vector_index.insert_nodes(nodes, transformations=transformations, storage_context=storage_context)

node_postprocessors = [MetadataReplacementPostProcessor(target_metadata_key="window"),SimilarityPostprocessor(similarity_cutoff=0.5)]
index_query_engine = index.as_query_engine(similarity_top_k=doc_similarity_top_k, node_postprocessors=node_postprocessors)

[1] node_parser = MarkdownElementNodeParser(llm=llm)
[2] nodes = node_parser.get_nodes_from_documents([document])
[3] base_nodes, objects = node_parser.get_nodes_and_objects(nodes)

import os
import pymongo
import ModelDef
from llama_index.core import VectorStoreIndex, StorageContext, SimpleDirectoryReader, set_global_service_context
from llama_index.llms.azure_openai import AzureOpenAI
from llama_index.embeddings.azure_openai import AzureOpenAIEmbedding
from llama_index.core.indices.vector_store.base import VectorStoreIndex
from llama_index.vector_stores.mongodb import MongoDBAtlasVectorSearch
from llama_index.core import Settings
from llama_index.core.indices.vector_store import VectorStoreIndex
import os
import pymongo
import json
import ModelDef
from flask import Flask, request

# ---------------------------
# Constantes de l'application
# ---------------------------

# Définition des models de déploiement AI

_modelGPT4o = ModelDef.ModelGPT("gpt-4o", "gpt-4o", "2024-10-21")
_modelAda2 = ModelDef.ModelGPT("ada2", "text-embedding-ada-002", "2024-10-21")

_server4o = ModelDef.ServerGPT("gpt4o", "https://.azure.com", "26f3ea90247b1a9286057d53c2539", "c59f1006a64015a7b083ed29", "eastus2", _modelGPT4o, _modelAda2)

_models = [ _server4o]
_model = _models[0]

# Constants

_index = "LeJourSeLeveIFC"
_directory = "C:\\Projets\\ifcdoctest"
_mongoURI = os.environ["MONGO_URI"] = "url of mongo data base"

# ----------------------
# Démarrage du programme
# ----------------------

# Initialisation OpenAI

print("Initialisation OpenAI...")

llm = AzureOpenAI(
    #model=_model.ChatModel.Model,
    #deployment_name=_model.ChatModel.Name,
    api_key=_model.Key1,
    azure_endpoint=_model.Server,
    api_version=_model.ChatModel.ApiVersion,
)

embed_model = AzureOpenAIEmbedding(
    model=_model.LearningModel.Model,
    deployment_name=_model.LearningModel.Name,
    api_key=_model.Key1,
    azure_endpoint=_model.Server,
    api_version=_model.LearningModel.ApiVersion,
)
#Settings.llm = AzureOpenAI(model=llm)
#Settings.embed_model = AzureOpenAIEmbedding(model=_modelAda2)
#service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model)
#set_global_service_context(service_context)
# Initialisation des paramètres pour les requètes sur MongoDB Atlas
print("Initialisation MongoDB...")

mongodb_client = pymongo.MongoClient(_mongoURI)
store = MongoDBAtlasVectorSearch(mongodb_client, db_name=_index)
storage_context = StorageContext.from_defaults(vector_store=store)

# On parcours chaque fichier
print("Démarrage de l'importation...")

reader = SimpleDirectoryReader(_directory, recursive=True, encoding="latin-1", required_exts=[".pdf", ".docx", ".pptx", ".csv", ".txt"])

for docs in reader.iter_data():
        print("F > " + docs[0].metadata['file_name'])
        VectorStoreIndex.from_documents(docs, storage_context=storage_context)
# Fin du programme

print("Terminée.")

vision_service-1        | pydantic_core._pydantic_core.ValidationError: 2 validation errors for ChatMessage
vision_service-1        | blocks.0
vision_service-1        |   Unable to extract tag using discriminator ‘block_type’ [type=union_tag_not_found, input_value={‘type’: ‘text’, ‘text’: ‘Describe what you see’}, input_type=dict]
vision_service-1        |     For further information visit https://errors.pydantic.dev/2.9/v/union_tag_not_found
vision_service-1        | blocks.1
vision_service-1        |   Unable to extract tag using discriminator ‘block_type’ [type=union_tag_not_found, input_value={‘type’: ‘image_url’, ‘im...gg==’, ‘detail’: ‘low’}}, input_type=dict]