Skip to main content

Drop-in hallucination-resistant retrieval for pgvector, ChromaDB, Pinecone, and Weaviate

Project description

prismrag-patch

Drop-in hallucination-resistant retrieval for your own vector database.

PrismRAG Patch wraps pgvector, ChromaDB, Pinecone, or Weaviate with PrismRAG's Tier-1 re-mapping technique — deterministic category projection that grounds every chunk in your verified rules before it ever reaches the LLM.

from prismrag_patch import PrismRAGPatch
from prismrag_patch.adapters.pgvector import PgvectorAdapter

mapping = {
    "categories": [
        {"slug": "risk",   "label": "Risk & Compliance"},
        {"slug": "growth", "label": "Growth"},
    ],
    "rules": [
        {"word": "volatility", "category_slug": "risk",   "weight": 1.0},
        {"word": "revenue",    "category_slug": "growth", "weight": 1.0},
    ],
}

patch   = PrismRAGPatch(license_key="prlib_…", mapping=mapping)
adapter = PgvectorAdapter(patch, connection=your_psycopg2_conn)

# Insert — re-mapped before storage
adapter.insert(text=doc, vector=embed(doc))

# Search — query re-mapped identically, no hallucination path
results = adapter.search("what is our risk exposure?", query_vector=q_vec)

Installation

pip install prismrag-patch                   # core only
pip install "prismrag-patch[pgvector]"       # + pgvector support
pip install "prismrag-patch[chroma]"         # + ChromaDB support
pip install "prismrag-patch[pinecone]"       # + Pinecone support
pip install "prismrag-patch[weaviate]"       # + Weaviate support
pip install "prismrag-patch[all]"            # all adapters

License

Commercial license required. Get yours at prismrag.insightits.com/prismrag-lib.html.

© 2026 Insight IT Solutions

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

prismrag_patch-0.1.0.tar.gz (10.4 kB view details)

Uploaded Source

Built Distribution

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

prismrag_patch-0.1.0-py3-none-any.whl (13.0 kB view details)

Uploaded Python 3

File details

Details for the file prismrag_patch-0.1.0.tar.gz.

File metadata

  • Download URL: prismrag_patch-0.1.0.tar.gz
  • Upload date:
  • Size: 10.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for prismrag_patch-0.1.0.tar.gz
Algorithm Hash digest
SHA256 25d0c914e8dfe8cb7c694b1c7122c558825fdeda43e6e28898b9e858007fb8d5
MD5 dc61114866610b9ec0d7d07766a72324
BLAKE2b-256 c2797c847912bc0f1d21df9ce182e6079f15604728bd548c82110b72b108245d

See more details on using hashes here.

File details

Details for the file prismrag_patch-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: prismrag_patch-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 13.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for prismrag_patch-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7f5616bca07a2a4cf3c426e41dd4ca96cd2af7f124cb8383eaed989719a84f2d
MD5 7a70f899cf87d7596687c9ade8781c11
BLAKE2b-256 022d5b1d25e28f4d8bdb4b3d372cd270384793142476c9aea50d1cbb7272cf4e

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