Query Engines und Antwortsynthese

query_engine = index.as_query_engine()
response = query_engine.query('What is our refund policy?')
print(response.response)         # the answer
print(response.source_nodes)     # the chunks used

query_engine = index.as_query_engine(response_mode='tree_summarize')

query_engine = index.as_query_engine(
    similarity_top_k=5,
    response_mode='compact'
)

from llama_index.core.prompts import PromptTemplate

qa_template = PromptTemplate(
    'Context:\n{context_str}\n\nQuestion: {query_str}\nAnswer:'
)
query_engine.update_prompts({'response_synthesizer:text_qa_template': qa_template})

query_engine = index.as_query_engine(streaming=True)
response = query_engine.query('Hello')
for token in response.response_gen:
    print(token, end='', flush=True)

from llama_index.core.query_engine import CitationQueryEngine

engine = CitationQueryEngine.from_args(index, similarity_top_k=4)
response = engine.query('What is our refund policy?')
print(response.response)
for i, node in enumerate(response.source_nodes):
    print(f'[{i+1}] {node.metadata}')

from llama_index.postprocessor.cohere_rerank import CohereRerank

rerank = CohereRerank(api_key=COHERE_KEY, top_n=3)
query_engine = index.as_query_engine(
    similarity_top_k=20,           # retrieve 20
    node_postprocessors=[rerank]   # rerank to top 3
)

from llama_index.core.vector_stores import MetadataFilters, ExactMatchFilter

filters = MetadataFilters(filters=[
    ExactMatchFilter(key='department', value='engineering')
])
query_engine = index.as_query_engine(filters=filters)

response = await query_engine.aquery('What is our refund policy?')
print(response.response)

chat_engine = index.as_chat_engine(chat_mode='context')
response = chat_engine.chat('What is our refund policy?')
followup = chat_engine.chat('And for opened items?')