extra_info parameter of the Node object. This metadata can be any key-value pairs that you want to associate with the node.from llama_index.data_structs.node import Node
nodes = [
Node('The Shawshank Redemption', extra_info={
"author": "Stephen King",
"theme": "Friendship",
}),
Node('The Godfather', extra_info={
"director": "Francis Ford Coppola",
"theme": "Mafia",
}),
Node("Inception", extra_info={
"director": "Christopher Nolan",
})
]SupabaseVectorStore, PineconeVectorStore, DocArrayHnswVectorStore, or DocArrayInMemoryVectorStore.from llama_index.storage.storage_context import StorageContext from llama_index.vector_stores import PineconeVectorStore vector_store = PineconeVectorStore(index_name="your_index_name") storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex(nodes, storage_context=storage_context)
MetadataFilters and ExactMatchFilter. You can include one or more of your metadata keys in the filters.``
**Source** (<https://gpt-index.readthedocs.io/en/latest/examples/vector_stores/SupabaseVectorIndexDemo.html>)
Remember to replace "your_index_name" with the name of your index, and "theme" and "Mafia" with your desired key and value for filtering.
----------------------
Note: you can ask me a follow up question by @ mentioning me again` :speech_balloon:Node object. This data typically represents a chunk of text from a document. Here's an example:from llama_index.data_structs.node import Node, DocumentRelationship node1 = Node(text="<text_chunk>", doc_id="<node_id>") node2 = Node(text="<text_chunk>", doc_id="<node_id>")
<text_chunk> is where you specify your data. Replace <text_chunk> with the actual text data you want to store in the node. Similarly, replace <node_id> with a unique identifier for each node.document = Document(
'text',
extra_info={
'filename': '<doc_file_name>',
'category': '<category>'
}
)'text' with your actual text data, <doc_file_name> with the filename of the document, and <category> with the category of the document.Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:ModuleNotFoundError: No module named 'llama_index.data_structs.node' typically occurs when the llama_index package is not installed in your Python environment, or your Python environment is not set up correctly.llama_index package using pip. Open your terminal and run the following command:pip install llama-index
llama_index is installed. If you're using a virtual environment, ensure that it's activated when you run your Python script.from llama_index.data_structs.node import Node
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:Document objects from text data, which are then parsed into Node objects.Document objects from the extracted text. Here's a basic example of how you might do this:import PyPDF2
from llama_index import Document
# Open the PDF file in binary mode
with open('your_file.pdf', 'rb') as file:
# Create a PDF file reader object
reader = PyPDF2.PdfFileReader(file)
# Get the text content from the PDF
text = ''
for page_num in range(reader.numPages):
page = reader.getPage(page_num)
text += page.extractText()
# Create a Document object from the text
document = Document(text)'your_file.pdf' with the path to your PDF file. After creating the Document object, you can then parse it into Node objects as per the usual LlamaIndex workflow.Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:Document objects. This metadata can be any key-value pairs that you want to associate with the document. The metadata is included in the extra_info parameter of the Document object.Document object.from llama_index import Document
document = Document(
'text',
extra_info={
'filename': '<doc_file_name>',
'category': '<category>'
}
)'text' with your actual text data, <doc_file_name> with the filename of the document, and <category> with the category of the document.Document object has been created.document.extra_info = {'filename': '<doc_file_name>'}<doc_file_name> with the filename of the document.SimpleDirectoryReader and file_metadata hook: This will automatically run the hook on each document to set the extra_info field.from llama_index import SimpleDirectoryReader
filename_fn = lambda filename: {'file_name': filename}
# automatically sets the extra_info of each document according to filename_fn
documents = SimpleDirectoryReader('./data', file_metadata=filename_fn)'./data' with the path to your directory of documents.extra_info dictionary of each document will show up in the extra_info of each source node created from the document. This information is included in the nodes, enabling the index to utilize it on queries and responses.Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: