giladnaor/ReplyOMeter
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixing some Markdown issues

Browse Source
This commit is contained in:
Gilad Naor 2024-09-09 08:48:05 -04:00
parent 112658894d
commit 4985c6456b
2 changed files with 18 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
Design.md
View File

@ -3,34 +3,34 @@ The purpose of this document is to align on the initial design of Reply-O-Meter.
## Overview ## Overview
The following is a product-oriented view of all the stages that need to happen in the final V1 product: The following is a product-oriented view of all the stages that need to happen in the final V1 product:
1. *Data Ingestions* *Data Ingestions*
Input: raw photos Input: raw photos
Output: List of Artifacts that link the raw photo with a textual representation Output: List of Artifacts that link the raw photo with a textual representation
a. Ingest all of the raw data files. Photos of letters, postcards, and photos. 1. Ingest all of the raw data files. Photos of letters, postcards, and photos.
b. Digitization: conversation of the data to a textual representation. 2. Digitization: conversation of the data to a textual representation.
c. Normalization: translation of all material to one internal language (e.g. English) 3. Normalization: translation of all material to one internal language (e.g. English)
d. Artifacts: creating Artifacts from joint raw material. Example: photos of person and the name/time from the photo's backside. 4. Artifacts: creating Artifacts from joint raw material. Example: photos of person and the name/time from the photo's backside.
2. *Data Processing* *Data Processing*
Input: List of Artifacts Input: List of Artifacts
Output: Graph of Entities (Person, Location, and Event) Output: Graph of Entities (Person, Location, and Event)
a. Metadata (move to Ingestino?): for each Artifact, extract the Metadata on the Entities that it refers to, such as Person, Event, and Location. 1. Metadata (move to Ingestino?): for each Artifact, extract the Metadata on the Entities that it refers to, such as Person, Event, and Location
b. Reconciliation: Create and/or Update existing Entities based on the information from the new Artifacts. 2. Reconciliation: Create and/or Update existing Entities based on the information from the new Artifacts.
3. *Browser* *Browser*
Input: Graph of Entities Input: Graph of Entities
Output: Updates to Artifacts and/or Entities Output: Updates to Artifacts and/or Entities
a. Feedback: User may correct any of the Ingestion or Processing steps, which will retrigger the rest of the flow. 1. Feedback: User may correct any of the Ingestion or Processing steps, which will retrigger the rest of the flow.
i. Will trigger model training/tuning if relevant. 2. Tuning: Will trigger model training/tuning if relevant.
4. *Story Creator* *Story Creator*
Input: Graph of Entities Input: Graph of Entities
Output: Story Output: Story
a. Chat Agent: User can chat with an Author to create stories based on the known Entities. 1. Chat Agent: User can chat with an Author to create stories based on the known Entities.
5. *Graphic Artist* *Graphic Artist*
Input: Story, Graph of Entities Input: Story, Graph of Entities
Output: Graphic Novel Output: Graphic Novel
a. People: Given a style, create visual representation for each Person across their life. 1. People: Given a style, create visual representation for each Person across their life.
b. Supporting Material: Gather maps of the Location and the relevant Events. 2. Supporting Material: Gather maps of the Location and the relevant Events.
c. Create a graphic novel based on the story. 3. Create a graphic novel based on the story.

2
README.md
View File

@ -1,3 +1,3 @@
# ReplyOMeter # ReplyOMeter
Please read the [PR-FAQ][PR-FAQ.md] document first. Please read the [PR-FAQ](PR-FAQ.md) document first.