هرمية الفهرسة: المتجه والشجرة والكلمات المفتاحية

الفهارس في LlamaIndex

VectorStoreIndex (الافتراضي)

from llama_index.core import VectorStoreIndex

index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
print(query_engine.query('What is in the handbook?'))

TreeIndex

from llama_index.core import TreeIndex

index = TreeIndex.from_documents(documents)
# Internal nodes are summaries of their children.
# Good for 'summarise the whole corpus' tasks.

KeywordTableIndex

from llama_index.core import KeywordTableIndex

index = KeywordTableIndex.from_documents(documents)
# Falls back to exact-match for rare technical terms.

SummaryIndex (المعروف سابقًا باسم ListIndex)

from llama_index.core import SummaryIndex

index = SummaryIndex.from_documents(documents)
# Best for short corpora where you can stuff everything into context.

KnowledgeGraphIndex

from llama_index.core import KnowledgeGraphIndex

index = KnowledgeGraphIndex.from_documents(
    documents,
    max_triplets_per_chunk=10
)

اختيار الفهرس

تركيب الفهارس

from llama_index.core import ComposableGraph

graph = ComposableGraph.from_indices(
    TreeIndex,
    [vector_index_doc_1, vector_index_doc_2, ...],
    index_summaries=['Doc 1 summary', 'Doc 2 summary']
)

Persisting an Index

index.storage_context.persist(persist_dir='./store')

# Reload later:
from llama_index.core import StorageContext, load_index_from_storage
ctx = StorageContext.from_defaults(persist_dir='./store')
index = load_index_from_storage(ctx)

استخدام مخازن المتجهات الخارجية

from llama_index.vector_stores.pinecone import PineconeVectorStore
from llama_index.core import StorageContext, VectorStoreIndex

vector_store = PineconeVectorStore(pinecone_index=pc_index)
storage = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage)

الاسترجاع الهجين

تحديث الفهرس

index.refresh_ref_docs(updated_documents)

فهرس التلخيص

مراجعة سريعة