Skip to main content

LlamaIndex integration for TruthVouch Trust API — hallucination detection and content verification

Project description

llama-index-truthvouch

LlamaIndex integration for the TruthVouch Trust API. Add hallucination detection and content verification to any LlamaIndex RAG pipeline in minutes.

Installation

pip install llama-index-truthvouch

Quickstart

import os
os.environ["TRUTHVOUCH_API_KEY"] = "your-api-key"

from truthvouch_llamaindex import TruthVouchResponseEvaluator

evaluator = TruthVouchResponseEvaluator(threshold=0.8)
result = await evaluator.evaluate("The Eiffel Tower is in Paris, France.")
print(result.passing)       # True
print(result.score)         # e.g. 0.96
print(result.feedback)      # human-readable explanation

Components

TrustApiClient

Low-level async/sync client for the Trust API verify endpoint.

from truthvouch_llamaindex import TrustApiClient

client = TrustApiClient(api_key="your-api-key")
result = client.verify_sync("The Eiffel Tower is in Paris.", mode="standard")
print(result.trust_score)  # 0.97

TruthVouchNodePostprocessor

Filters retrieved nodes by trust score before they reach the LLM.

from llama_index.core import VectorStoreIndex
from truthvouch_llamaindex import TruthVouchNodePostprocessor

postprocessor = TruthVouchNodePostprocessor(threshold=0.75)
query_engine = index.as_query_engine(node_postprocessors=[postprocessor])
response = query_engine.query("What is the capital of France?")

TruthVouchResponseEvaluator

Evaluate a RAG response string for factual accuracy.

from truthvouch_llamaindex import TruthVouchResponseEvaluator

evaluator = TruthVouchResponseEvaluator(threshold=0.8)
result = await evaluator.evaluate("Some response text")
if not result.passing:
    print("Hallucination risk:", result.feedback)

TruthVouchQueryEngine

Wrapper query engine that auto-verifies every response.

from truthvouch_llamaindex import TruthVouchQueryEngine

engine = TruthVouchQueryEngine(inner_query_engine=base_engine, threshold=0.8)
response = engine.query("Tell me about the Eiffel Tower.")
print(response.metadata["trust_score"])

Configuration

Parameter Env var Default
api_key TRUTHVOUCH_API_KEY (required)
base_url http://localhost:5004/api/v1/trust
threshold 0.8
mode spot_check

License

Apache-2.0

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

llama_index_truthvouch-1.0.0.tar.gz (15.7 kB view details)

Uploaded Source

Built Distribution

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

llama_index_truthvouch-1.0.0-py3-none-any.whl (14.4 kB view details)

Uploaded Python 3

File details

Details for the file llama_index_truthvouch-1.0.0.tar.gz.

File metadata

  • Download URL: llama_index_truthvouch-1.0.0.tar.gz
  • Upload date:
  • Size: 15.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for llama_index_truthvouch-1.0.0.tar.gz
Algorithm Hash digest
SHA256 5b276c69bd2001c69aefa37b49ad86fcf6efb82536bc1dedfc6f9a62ea24ab95
MD5 98038b416e01dde0890b6ab14acb4c1d
BLAKE2b-256 9f063cee2d8f0467ba55ca91bc84ac2cec2c788e8bab6375637f8393d723ab32

See more details on using hashes here.

File details

Details for the file llama_index_truthvouch-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for llama_index_truthvouch-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e5c44800177747342bcdbd1b17f1a7fffd2b274767fbe36b4cba87a25daf8fcf
MD5 9ca3295ccd827852eebc0d1df96121ca
BLAKE2b-256 76904b886c3b53f832e57d030832a8700b99c44b5f807c86cb2edea076d3e7cd

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