Contextual Reranker

This is a Llama_index package that calls Contextual's /rerank endpoint. It will rank a list of documents according to their relevance to a query.

The total request cannot exceed 400,000 tokens. The combined length of any document, instruction and the query must not exceed 4,000 tokens. Email rerank-feedback@contextual.ai with any feedback or questions.

Usage

from llama_index.postprocessor.contextual_rerank import ContextualRerank
from llama_index.core.schema import NodeWithScore, TextNode

nodes = [
    NodeWithScore(node=TextNode(text="the capital of france is paris")),
    NodeWithScore(
        node=TextNode(text="the capital of the United States is Washington DC")
    ),
]

query = "What is the capital of France?"

contextual_rerank = ContextualRerank(
    api_key="key-...",
    model="ctxl-rerank-en-v1-instruct",
    top_n=2,
)

response = contextual_rerank.postprocess_nodes(nodes, query_str=query)

for node in response:
    print(node)

Download files

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

Source Distribution

llama_index_postprocessor_contextual_rerank-0.4.0.tar.gz (3.8 kB view details)

Uploaded Aug 31, 2026 Source

Built Distribution

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

llama_index_postprocessor_contextual_rerank-0.4.0-py3-none-any.whl (4.4 kB view details)

Uploaded Aug 31, 2026 Python 3

File details

Details for the file llama_index_postprocessor_contextual_rerank-0.4.0.tar.gz.

File metadata

Download URL: llama_index_postprocessor_contextual_rerank-0.4.0.tar.gz
Upload date: Aug 31, 2026
Size: 3.8 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for llama_index_postprocessor_contextual_rerank-0.4.0.tar.gz
Algorithm	Hash digest
SHA256	`5026db0673b039903eb1408c2524a1e95e5376f408c1dc41f3813dca1812d053`
MD5	`c20baaa340707ebc795edcd4bcd5a7f5`
BLAKE2b-256	`22a766826f633bbbed1a29d53ba612079e1aaa6c51f26863502ecc1ac32c7849`

See more details on using hashes here.

File details

Details for the file llama_index_postprocessor_contextual_rerank-0.4.0-py3-none-any.whl.

File metadata

Download URL: llama_index_postprocessor_contextual_rerank-0.4.0-py3-none-any.whl
Upload date: Aug 31, 2026
Size: 4.4 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for llama_index_postprocessor_contextual_rerank-0.4.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`e0ace3d8325f9a6e3112d2f9d35a9dba4c304139ab3c29842414f5f4cf3b5e7e`
MD5	`4d4d0673dfaf6ca5edcbfb1a73aa6513`
BLAKE2b-256	`389538695133572f3cb5e494820306f28c2dfabb9b3fc28321efa30f47517039`