Skip to main content

llama-index postprocessor reranker models from pinecone cloud service

Project description

LLamaIndex node postprocessing reranker using pinecone hosted models

  • use rerank models with the pinecone managed vector service to rerank the search results
  • available rerank models from pinecone
import os
from llama_index.core import VectorStoreIndex
from llama_index.core.schema import TextNode
from llama_index.postprocessor.pinecone_native_rerank import (
    PineconeNativeRerank,
)
from llama_index.core.response.pprint_utils import pprint_response

os.environ["PINECONE_API_KEY"] = "your_pinecone_api_key"
os.environ["OPENAI_API_KEY"] = "your_openai_api_key"

txts = [
    "Apple is a popular fruit known for its sweetness and crisp texture.",
    "Apple is known for its innovative products like the iPhone.",
    "Many people enjoy eating apples as a healthy snack.",
    "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces.",
    "An apple a day keeps the doctor away, as the saying goes.",
    "apple has a lot of vitamins",
]

nodes = [TextNode(id_=f"vec{i}", text=txt) for i, txt in enumerate(txts)]

pinecone_reranker = PineconeNativeRerank(top_n=4, model="pinecone-rerank-v0")

index = VectorStoreIndex(nodes)

query_engine = index.as_query_engine(
    similarity_top_k=10,
    node_postprocessors=[pinecone_reranker],
)

response = query_engine.query(
    "The tech company Apple is known for its innovative products like the iPhone."
)

pprint_response(response, show_source=True)

output

Final Response: Apple is recognized for its innovative products like
the iPhone.
______________________________________________________________________
Source Node 1/4
Node ID: vec1
Similarity: 0.9655668
Text: Apple is known for its innovative products like the iPhone.
______________________________________________________________________
Source Node 2/4
Node ID: vec3
Similarity: 0.55420566
Text: Apple Inc. has revolutionized the tech industry with its sleek
designs and user-friendly interfaces.
______________________________________________________________________
Source Node 3/4
Node ID: vec4
Similarity: 0.3172258
Text: An apple a day keeps the doctor away, as the saying goes.
______________________________________________________________________
Source Node 4/4
Node ID: vec0
Similarity: 0.25139993
Text: Apple is a popular fruit known for its sweetness and crisp
texture.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file llama_index_postprocessor_pinecone_native_rerank-0.2.1.tar.gz.

File metadata

File hashes

Hashes for llama_index_postprocessor_pinecone_native_rerank-0.2.1.tar.gz
Algorithm Hash digest
SHA256 7c3c37a291696f28711384686aee5503f367976b44fd079cfdac6c72c329fb86
MD5 ac8239cd9a7edfb90dd3623ffe8a8767
BLAKE2b-256 ac20cab4050d092e18fffa9bcef23e418983ea5eb3b2867f056322e2d8e49c9d

See more details on using hashes here.

File details

Details for the file llama_index_postprocessor_pinecone_native_rerank-0.2.1-py3-none-any.whl.

File metadata

File hashes

Hashes for llama_index_postprocessor_pinecone_native_rerank-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 caa42ac702423bc2a4e53f3471d9fc5f4477b1e97ffecce9dccbb6379be1b262
MD5 7b9849cc391612c73cbc4bfb55a8f013
BLAKE2b-256 cc0fec0ee4bcc95d3eb03f41b1f574908e7cdca1a1d8b1bf43a5d2232d73c66e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page