Skip to main content

matrx-rag

Multi-tenant RAG: hybrid retrieval, chunking, embeddings, ingestion, PDF + image + repo pipelines, agent-extraction indexing, NER/KG writes, priority-aware ranking — extracted from aidream/services/rag/ so any host (aidream's cloud server, matrx-local) can consume the same stack.

Cross-repo system-of-record: /Users/armanisadeghi/code/common-docs/systems/knowledge/rag/STATE.md — read it before touching this feature in ANY repo.

Editing rules for this package: CLAUDE.md · matrx_rag/FEATURE.md.

What it does

  • Ingestion: ingest_source(source_kind, source_id, ...) — chunk → embed → upsert; NER inline for non-code sources.
  • PDF / image / code repo pipelines with provenance.
  • Hybrid search: pgvector HNSW + lexical FTS → RRF → optional Cohere → MMR.
  • Priority-aware ranking: agent-extracted chunks with non-zero priority.
  • Agent-extraction → RAG: extraction_indexing materializes page-extraction payloads as chunks.
  • Data stores: curated buckets with scoped search.
  • Eval harness: retrieval + answer quality assessment.

Host integration

  • aidream wires the package in aidream/package_integration.py::_configure_matrx_rag (NER extractor, embedding cache, ORM models, search callable).
  • aidream/services/rag/ is a re-export shim; HTTP routes live in aidream/api/routers/rag.py.
  • Auto-ingest (gates, budget, scope suggestions) lives in aidream/services/auto_ingest/ — not in this package.

Schema

Migrations: matrx_rag/migrations/ (mirrored in db/migrations/ until package owns the runner).
ORM / pgvector notes: /Users/armanisadeghi/code/common-docs/projects/knowledge-system/reality/code-truth/04_ORM_AND_SCHEMA.md.

Package development

See CLAUDE.md for injection seams, test baselines, and the no-aidream-imports rule.

Download files

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

Source Distribution

matrx_rag-0.1.191.tar.gz (403.5 kB view details)

Uploaded Source

Built Distribution

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

matrx_rag-0.1.191-py3-none-any.whl (442.8 kB view details)

Uploaded Python 3

File details

Details for the file matrx_rag-0.1.191.tar.gz.

File metadata

  • Download URL: matrx_rag-0.1.191.tar.gz
  • Upload date:
  • Size: 403.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for matrx_rag-0.1.191.tar.gz
Algorithm Hash digest
SHA256 4833020117ed3d110c2f72453f28e7d7904e267b20abb29ece10418038d0db7c
MD5 b0859ba469d02c375aa0135f8f331e0c
BLAKE2b-256 0a8060a0ab125e741d09a73257d060ba22e1f6beee75ad92ee31fc9149d79acc

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_rag-0.1.191.tar.gz:

Publisher: publish-package.yml on AI-Matrix-Engine/aidream

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file matrx_rag-0.1.191-py3-none-any.whl.

File metadata

  • Download URL: matrx_rag-0.1.191-py3-none-any.whl
  • Upload date:
  • Size: 442.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for matrx_rag-0.1.191-py3-none-any.whl
Algorithm Hash digest
SHA256 92a81ea0f2c6ae8b01bcd1519dc9aad3d46153ba8fe08fcf4cf8ec13f691cb1a
MD5 9acb63903c6619ea44b782d53ee7e848
BLAKE2b-256 5b587eb237450f3d4ff33d5f8d87fa930fcbb871c5dc1e415712333522f1177c

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_rag-0.1.191-py3-none-any.whl:

Publisher: publish-package.yml on AI-Matrix-Engine/aidream

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.1.192

2 files

This release

0.1.191 This release

2 files

0.1.190

2 files

0.1.189

2 files

0.1.188

2 files

0.1.187

2 files

0.1.186

2 files

0.1.185

2 files

0.1.184

2 files

0.1.183

2 files

0.1.182

2 files

0.1.181

2 files

0.1.180

2 files

0.1.179

2 files

0.1.178

2 files

0.1.177

2 files

0.1.176

2 files

0.1.175

2 files

0.1.174

2 files

0.1.173

2 files

0.1.172

2 files

0.1.171

2 files

0.1.170

2 files

0.1.169

2 files

0.1.168

2 files

0.1.167

2 files

0.1.166

2 files

0.1.165

2 files

0.1.164

2 files

0.1.163

2 files

0.1.162

2 files

0.1.161

2 files

0.1.160

2 files

0.1.159

2 files

0.1.158

2 files

0.1.157

2 files

0.1.156

2 files

0.1.155

2 files

0.1.154

2 files

0.1.153

2 files

0.1.152

2 files

0.1.151

2 files

0.1.150

2 files

0.1.149

2 files

0.1.148

2 files

0.1.147

2 files

0.1.146

2 files

0.1.145

2 files

0.1.144

2 files

0.1.143

2 files

0.1.142

2 files

0.1.141

2 files

0.1.140

2 files

0.1.139

2 files

0.1.138

2 files

0.1.137

2 files

0.1.136

2 files

0.1.135

2 files

0.1.134

2 files

0.1.133

2 files

0.1.132

2 files

0.1.131

2 files

0.1.130

2 files

0.1.129

2 files

0.1.128

2 files

0.1.127

2 files

0.1.126

2 files

0.1.125

2 files

0.1.124

2 files

0.1.123

2 files

0.1.122

2 files

0.1.121

2 files

0.1.120

2 files

0.1.119

2 files

0.1.118

2 files

0.1.117

2 files

0.1.116

2 files

0.1.115

2 files

0.1.114

2 files

0.1.113

2 files

0.1.112

2 files

0.1.111

2 files

0.1.110

2 files

0.1.109

2 files

0.1.108

2 files

0.1.107

2 files

0.1.106

2 files

0.1.105

2 files

0.1.104

2 files

0.1.103

2 files

0.1.102

2 files

0.1.101

2 files

0.1.100

2 files

0.1.99

2 files

0.1.98

2 files

0.1.97

2 files

0.1.96

2 files

0.1.95

2 files

0.1.94

2 files

0.1.93

2 files

0.1.92

2 files

0.1.91

2 files

0.1.90

2 files

0.1.89

2 files

0.1.88

2 files

0.1.87

2 files

0.1.86

2 files

0.1.85

2 files

0.1.84

2 files

0.1.83

2 files

0.1.82

2 files

0.1.81

2 files

0.1.80

2 files

0.1.79

2 files

0.1.78

2 files

0.1.77

2 files

0.1.76

2 files

0.1.75

2 files

0.1.74

2 files

0.1.73

2 files

0.1.72

2 files

0.1.71

2 files

0.1.70

2 files

0.1.69

2 files

0.1.68

2 files

0.1.67

2 files

0.1.66

2 files

0.1.65

2 files

0.1.64

2 files

0.1.63

2 files

0.1.62

2 files

0.1.61

2 files

0.1.60

2 files

0.1.59

2 files

0.1.58

2 files

0.1.57

2 files

0.1.56

2 files

0.1.55

2 files

0.1.54

2 files

0.1.53

2 files

0.1.52

2 files

0.1.51

2 files

0.1.50

2 files

0.1.49

2 files

0.1.48

2 files

0.1.47

2 files

0.1.46

2 files

0.1.45

2 files

0.1.44

2 files

0.1.43

2 files

0.1.42

2 files

0.1.41

2 files

0.1.40

2 files

0.1.39

2 files

0.1.38

2 files

0.1.37

2 files

0.1.36

2 files

0.1.35

2 files

0.1.34

2 files

0.1.33

2 files

0.1.32

2 files

0.1.31

2 files

0.1.30

2 files

0.1.29

2 files

0.1.28

2 files

0.1.27

2 files

0.1.26

2 files

0.1.25

2 files

0.1.24

2 files

0.1.23

2 files

0.1.22

2 files

0.1.21

2 files

0.1.20

2 files

0.1.19

2 files

0.1.18

2 files

0.1.17

2 files

0.1.16

2 files

0.1.15

2 files

0.1.14

2 files

0.1.13

2 files

0.1.12

2 files

0.1.11

2 files

0.1.10

2 files

0.1.9

2 files

0.1.8

2 files

0.1.7

2 files

0.1.6

2 files

0.1.5

2 files

0.1.4

2 files

0.1.3

2 files

0.1.2

2 files

0.1.1

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page