Spaces:
Sleeping
Sleeping
Create README.md
Browse files
README.md
CHANGED
|
@@ -4,76 +4,174 @@ emoji: ποΈ
|
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version:
|
| 8 |
app_file: app.py
|
| 9 |
-
pinned:
|
| 10 |
tags:
|
| 11 |
- foia
|
| 12 |
-
- public-records
|
| 13 |
- government-transparency
|
|
|
|
| 14 |
- journalism
|
| 15 |
- open-data
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# Federal FOIA Intelligence Search
|
| 19 |
|
| 20 |
**Public Electronic Reading Rooms Only**
|
| 21 |
|
| 22 |
-
This Hugging Face Space provides a federated search interface
|
| 23 |
-
**publicly
|
|
|
|
|
|
|
| 24 |
|
| 25 |
---
|
| 26 |
|
| 27 |
## π What This Space Does
|
| 28 |
-
|
| 29 |
-
-
|
| 30 |
-
-
|
| 31 |
-
-
|
|
|
|
|
|
|
| 32 |
|
| 33 |
---
|
| 34 |
|
| 35 |
## ποΈ Live Public Sources
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
-
|
| 40 |
-
-
|
| 41 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
---
|
| 44 |
|
| 45 |
-
## π Hosted Public Collections
|
| 46 |
-
|
| 47 |
-
do **not**
|
|
|
|
|
|
|
| 48 |
|
| 49 |
-
|
| 50 |
-
- Clearly labeled as **Hosted Public Releases**
|
| 51 |
- Linked to the **original publishing agency**
|
| 52 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
|
| 54 |
---
|
| 55 |
|
| 56 |
## βοΈ What This Space Does NOT Do
|
|
|
|
| 57 |
β No classified access
|
| 58 |
β No scraping behind authentication
|
|
|
|
| 59 |
β No intelligence analysis or inference
|
| 60 |
-
β No automated FOIA
|
|
|
|
| 61 |
|
| 62 |
---
|
| 63 |
|
| 64 |
-
##
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
---
|
| 71 |
|
| 72 |
-
##
|
| 73 |
-
|
| 74 |
-
-
|
| 75 |
-
-
|
| 76 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
-
|
| 79 |
-
|
|
|
|
| 4 |
colorFrom: blue
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 4.44.0
|
| 8 |
app_file: app.py
|
| 9 |
+
pinned: true
|
| 10 |
tags:
|
| 11 |
- foia
|
|
|
|
| 12 |
- government-transparency
|
| 13 |
+
- public-records
|
| 14 |
- journalism
|
| 15 |
- open-data
|
| 16 |
+
- legal-tech
|
| 17 |
+
- oversight
|
| 18 |
+
license: mit
|
| 19 |
+
short_description: 'FOIA INTELLIGENCE SEARCH '
|
| 20 |
---
|
| 21 |
|
| 22 |
# Federal FOIA Intelligence Search
|
| 23 |
|
| 24 |
**Public Electronic Reading Rooms Only**
|
| 25 |
|
| 26 |
+
This Hugging Face Space provides a federated search and analysis interface for
|
| 27 |
+
**publicly released U.S. Government records made available under the Freedom of Information Act (FOIA)**.
|
| 28 |
+
|
| 29 |
+
It is designed for **journalists, researchers, legal professionals, oversight bodies, and the public**.
|
| 30 |
|
| 31 |
---
|
| 32 |
|
| 33 |
## π What This Space Does
|
| 34 |
+
|
| 35 |
+
- Searches **only publicly accessible FOIA Electronic Reading Rooms**
|
| 36 |
+
- Uses **official agency search endpoints or public landing pages**
|
| 37 |
+
- Enforces **robots.txt, rate limiting, and safe defaults**
|
| 38 |
+
- Provides **semantic search, clustering, and visualization**
|
| 39 |
+
- Generates **court-ready citations and FOIA request packets**
|
| 40 |
|
| 41 |
---
|
| 42 |
|
| 43 |
## ποΈ Live Public Sources
|
| 44 |
+
|
| 45 |
+
This Space currently supports live querying or indexed access to the following **public FOIA repositories**:
|
| 46 |
+
|
| 47 |
+
- **CIA FOIA Electronic Reading Room**
|
| 48 |
+
- **FBI Vault**
|
| 49 |
+
- **NSA FOIA Library**
|
| 50 |
+
- **Department of Defense FOIA Reading Room**
|
| 51 |
+
- **National Reconnaissance Office (NRO) Declassified Releases**
|
| 52 |
+
- **Department of Justice (DOJ) FOIA Library**
|
| 53 |
+
- **Department of Homeland Security (DHS) FOIA Library**
|
| 54 |
+
- **U.S. Department of State FOIA Reading Room**
|
| 55 |
+
|
| 56 |
+
All access is:
|
| 57 |
+
- Public
|
| 58 |
+
- Unauthenticated
|
| 59 |
+
- Non-privileged
|
| 60 |
+
- Read-only
|
| 61 |
|
| 62 |
---
|
| 63 |
|
| 64 |
+
## π Hosted Public Collections (Clearly Labeled)
|
| 65 |
+
|
| 66 |
+
Some historically named programs or collections (e.g. **AATIP**, **Special Access Programs**, **Special Activities**) do **not** operate independent FOIA portals.
|
| 67 |
+
|
| 68 |
+
When these appear in the interface, they are:
|
| 69 |
|
| 70 |
+
- Explicitly labeled as **Hosted Public Releases**
|
|
|
|
| 71 |
- Linked to the **original publishing agency**
|
| 72 |
+
- Limited to **already-declassified, publicly released documents**
|
| 73 |
+
- Included for **historical research and transparency**
|
| 74 |
+
|
| 75 |
+
No restricted or classified systems are accessed.
|
| 76 |
+
|
| 77 |
+
---
|
| 78 |
+
|
| 79 |
+
## π Analytics & Visualization Features
|
| 80 |
+
|
| 81 |
+
- **Real-time agency coverage heatmap** (documents per agency)
|
| 82 |
+
- **Latency & health indicators** per source
|
| 83 |
+
- **Interactive semantic cluster graph** (Plotly)
|
| 84 |
+
- **Timeline views** for document release dates
|
| 85 |
+
- **Result deduplication and clustering**
|
| 86 |
+
|
| 87 |
+
---
|
| 88 |
+
|
| 89 |
+
## π§ Semantic Search
|
| 90 |
+
|
| 91 |
+
- Uses **sentence-transformers + FAISS**
|
| 92 |
+
- Supports:
|
| 93 |
+
- Semantic clustering
|
| 94 |
+
- Search-within-results
|
| 95 |
+
- Topic grouping
|
| 96 |
+
- No model training on classified or private data
|
| 97 |
+
|
| 98 |
+
---
|
| 99 |
+
|
| 100 |
+
## π§Ύ Legal & Journalistic Tools
|
| 101 |
+
|
| 102 |
+
- **Court-ready Bluebook citation PDF export**
|
| 103 |
+
- **Journalist ZIP export** (documents + index)
|
| 104 |
+
- **FOIA request packet generator** (PDF / text)
|
| 105 |
+
- **FOIA exemption (b-code) labeling** (heuristic, informational only)
|
| 106 |
+
|
| 107 |
+
> β οΈ FOIA requests are **generated only**.
|
| 108 |
+
> This Space does **not** submit requests on behalf of users.
|
| 109 |
|
| 110 |
---
|
| 111 |
|
| 112 |
## βοΈ What This Space Does NOT Do
|
| 113 |
+
|
| 114 |
β No classified access
|
| 115 |
β No scraping behind authentication
|
| 116 |
+
β No bypassing agency safeguards
|
| 117 |
β No intelligence analysis or inference
|
| 118 |
+
β No automated FOIA submissions
|
| 119 |
+
β No user tracking beyond standard HF analytics
|
| 120 |
|
| 121 |
---
|
| 122 |
|
| 123 |
+
## π Legal Basis
|
| 124 |
+
|
| 125 |
+
All content accessed through:
|
| 126 |
+
|
| 127 |
+
- **5 U.S.C. Β§ 552 (Freedom of Information Act)**
|
| 128 |
+
- Agency-maintained **Electronic Reading Rooms**
|
| 129 |
+
- Public U.S. Government websites
|
| 130 |
+
|
| 131 |
+
This Space operates entirely within:
|
| 132 |
+
- U.S. law
|
| 133 |
+
- Agency publication rules
|
| 134 |
+
- Hugging Face platform policies
|
| 135 |
|
| 136 |
---
|
| 137 |
|
| 138 |
+
## π‘οΈ Safety & Governance
|
| 139 |
+
|
| 140 |
+
- Robots.txt enforcement per adapter
|
| 141 |
+
- Per-agency rate limits
|
| 142 |
+
- Per-agency kill switches
|
| 143 |
+
- Health monitoring & auto-disable
|
| 144 |
+
- Adapter compliance tests (CI)
|
| 145 |
+
|
| 146 |
+
---
|
| 147 |
+
|
| 148 |
+
## π― Intended Use
|
| 149 |
+
|
| 150 |
+
This project is intended to support:
|
| 151 |
+
|
| 152 |
+
- Investigative journalism
|
| 153 |
+
- Academic and historical research
|
| 154 |
+
- Legal review and litigation support
|
| 155 |
+
- Government oversight
|
| 156 |
+
- Public transparency initiatives
|
| 157 |
+
|
| 158 |
+
---
|
| 159 |
+
|
| 160 |
+
## π¬ Disclaimer
|
| 161 |
+
|
| 162 |
+
This tool aggregates and analyzes **public information only**.
|
| 163 |
+
It does not provide legal advice, intelligence assessments, or official interpretations.
|
| 164 |
+
|
| 165 |
+
Users are responsible for verifying primary sources.
|
| 166 |
+
|
| 167 |
+
---
|
| 168 |
+
|
| 169 |
+
## π¦ Open Source & Transparency
|
| 170 |
+
|
| 171 |
+
All adapters, logic, and safety mechanisms are visible in the source code.
|
| 172 |
+
No hidden data sources or privileged access exist.
|
| 173 |
+
|
| 174 |
+
---
|
| 175 |
|
| 176 |
+
**Federal FOIA Intelligence Search**
|
| 177 |
+
*Making public records easier to find, understand, and cite.*
|