mstoeck3/semeion
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

lint markdown, representative image

Browse Source
This commit is contained in:
Mario Stöckl
2025-11-25 15:25:40 +01:00
parent fe9b497d85
commit 22e4c4d4df
2 changed files with 7 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
Gemini_Generated_Image_wv24iuwv24iuwv24.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.6 MiB

13
README.md
View File

@@ -1,6 +1,6 @@
# Gamayun - # Gamayun
# Forensic Semantic Search System ![alt text](Gemini_Generated_Image_wv24iuwv24iuwv24.png)
## Concept ## Concept
@@ -13,7 +13,6 @@ This enables the combination of semantic understanding with context and temporal
An investigator can ask "show me what happened after they discussed the payment" and the system will find relevant communication about payments, then correlate subsequent activities (file access, application launches, network traffic) in a temporal sequence, regardless of the specific applications or messaging platforms involved. An investigator can ask "show me what happened after they discussed the payment" and the system will find relevant communication about payments, then correlate subsequent activities (file access, application launches, network traffic) in a temporal sequence, regardless of the specific applications or messaging platforms involved.
## System Overview ## System Overview
### Core Concept ### Core Concept
@@ -32,8 +31,6 @@ Client-Server Separation: Compute-intensive operations (embedding generation, LL
- Deployment in air-gapped labs - Deployment in air-gapped labs
- Efficient resource utilization (centralized compute nodes can serve multiple investigators) - Efficient resource utilization (centralized compute nodes can serve multiple investigators)
## Data Flow ## Data Flow
### Ingestion Pipeline ### Ingestion Pipeline
@@ -162,7 +159,6 @@ Natural Language Query
| NLP | spaCy | TBD | MIT | Entity extraction | | NLP | spaCy | TBD | MIT | Entity extraction |
| Programming Language | Python | 3.13+ | PSF | Application logic | | Programming Language | Python | 3.13+ | PSF | Application logic |
### Infrastructure Requirements ### Infrastructure Requirements
#### Remote Processing #### Remote Processing
@@ -203,10 +199,10 @@ TBD
### Secondary: Conversion Engine (algorithmic) ### Secondary: Conversion Engine (algorithmic)
Example: Example:
- SQLite Parser for browser History -> Special Data Object - SQLite Parser for browser History -> Special Data Object
- Converter for TSK artifacts -> Metadata in Special Data Object (TBD) - Converter for TSK artifacts -> Metadata in Special Data Object (TBD)
## Use Case Scenarios ## Use Case Scenarios
### Scenario 1: Drug Transaction Investigation ### Scenario 1: Drug Transaction Investigation
@@ -246,5 +242,6 @@ Query: "What happened between receiving the threatening email and deleting files
3. Returns all artifacts between these timestamps 3. Returns all artifacts between these timestamps
4. Visualizes complete timeline Evidence: Establishes sequence of events and potential motive 4. Visualizes complete timeline Evidence: Establishes sequence of events and potential motive
# License ## License
BSD 3-Clause (subject to change during development) BSD 3-Clause (subject to change during development)