ad-agent_architecture 0.0.5 → 0.0.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +8 -0
- data/docs/requirements.md +62 -0
- data/lib/ad/agent_architecture/version.rb +1 -1
- data/package-lock.json +2 -2
- data/package.json +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: daa2d7eacfdb1c2650cf23106d3f001040d765d7aa3ccf44081a989361e9ad48
|
|
4
|
+
data.tar.gz: b3fe1ef5e9d26a809d13ddb6200d125a17549b6af88b5995ba05e35788fcb608
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: b09d423f903b09b704e958627b4a2cc4d1dbae248aee623e0750623e366f13247ab943043742702f8e0353ce4fe8a22ea7303f0f267a2ccce90c365239970947
|
|
7
|
+
data.tar.gz: be77db10d9e1fc55d9d18464714b57a8039b194a5c53ec963d7becdc743533ef60b06af6d18cf9ba13048446d09031d679fe239c3c5c3352870a8b3cbeac706f
|
data/CHANGELOG.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
|
1
|
+
## [0.0.5](https://github.com/appydave/ad-agent_architecture/compare/v0.0.4...v0.0.5) (2024-06-28)
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
### Bug Fixes
|
|
5
|
+
|
|
6
|
+
* add sqlite3, sequal and setup a schema ([a8fa9c9](https://github.com/appydave/ad-agent_architecture/commit/a8fa9c9ff29ed223644d3622bd46ca5d626af9a9))
|
|
7
|
+
* add sqlite3, sequal and setup a schema ([87ded1e](https://github.com/appydave/ad-agent_architecture/commit/87ded1e6886d3190fc83ecaa4e215bacf044378f))
|
|
8
|
+
|
|
1
9
|
## [0.0.4](https://github.com/appydave/ad-agent_architecture/compare/v0.0.3...v0.0.4) (2024-06-26)
|
|
2
10
|
|
|
3
11
|
|
data/docs/requirements.md
CHANGED
|
@@ -1,3 +1,65 @@
|
|
|
1
|
+
# AppyDave - Agent Architecture Schema
|
|
2
|
+
|
|
3
|
+
## Purpose
|
|
4
|
+
|
|
5
|
+
The application is designed to handle structured workflows for building documents or text-based assets using LLMs from OpenAi, Anthropic and others. It should be adaptable to any workflow that follows a structured concept or a series of steps.
|
|
6
|
+
|
|
7
|
+
## Sample Workflows
|
|
8
|
+
- YouTube titles
|
|
9
|
+
- YouTube scripts
|
|
10
|
+
- YouTube transcription to Medium, LinkedIn, etc.
|
|
11
|
+
|
|
12
|
+
## Key Components
|
|
13
|
+
|
|
14
|
+
### Static Workflow Definition
|
|
15
|
+
- **Workflows**: Define a series of tasks to achieve a specific goal.
|
|
16
|
+
- **Sections**: Subdivisions within workflows to organize steps logically.
|
|
17
|
+
- **Steps**: Individual tasks within a section, each associated with an AI prompt and various input/output attributes.
|
|
18
|
+
- **Attributes**: Parameters used in steps, which can be simple values or arrays.
|
|
19
|
+
- **Input/Output Attributes**: Map attributes to steps as either inputs or outputs.
|
|
20
|
+
|
|
21
|
+
### Dynamic Workflow Execution
|
|
22
|
+
- **Workflow Runs**: Instances of workflow executions.
|
|
23
|
+
- **Section Runs**: Instances of section executions within a workflow run.
|
|
24
|
+
- **Step Runs**: Instances of step executions within a section run, supporting multiple branches.
|
|
25
|
+
- **Attribute Values**: Store the values of attributes during step executions.
|
|
26
|
+
|
|
27
|
+
## Features
|
|
28
|
+
|
|
29
|
+
### Schema Creation and Models
|
|
30
|
+
- Use Sequel and SQLite to define and manage the database schema.
|
|
31
|
+
- Models are defined for workflows, sections, steps, attributes, and their relationships.
|
|
32
|
+
|
|
33
|
+
### Testing and Validation
|
|
34
|
+
- Unit tests to verify the schema and associations using RSpec.
|
|
35
|
+
- Guard setup to automatically run tests when certain files are modified.
|
|
36
|
+
|
|
37
|
+
### Data Management
|
|
38
|
+
- Methods to export the database schema and data to JSON files for backup.
|
|
39
|
+
- Methods to restore the database from JSON files for easy editing and re-importing.
|
|
40
|
+
|
|
41
|
+
## Initial Workflows
|
|
42
|
+
- These include YouTube video scripts, YouTube title creation, and transcription to articles.
|
|
43
|
+
- These workflows serve as examples and validation for the broader concept.
|
|
44
|
+
|
|
45
|
+
## Implementation Details
|
|
46
|
+
- **Database**: Use SQLite with Sequel for ORM.
|
|
47
|
+
- **Code Structure**: Organize code into modules and classes for database schema creation and model definitions.
|
|
48
|
+
- **Testing**: Ensure models and associations are correctly implemented and tested.
|
|
49
|
+
|
|
50
|
+
## Next Steps
|
|
51
|
+
|
|
52
|
+
### Refine DSL for Static Workflows
|
|
53
|
+
- Enhance the DSL to create and update static workflows.
|
|
54
|
+
- Ensure it updates the database and exports workflows in JSON/YAML format.
|
|
55
|
+
- Implement rendering of the workflow structure as HTML.
|
|
56
|
+
|
|
57
|
+
### Plan Dynamic Execution
|
|
58
|
+
- Determine the approach for executing workflows dynamically.
|
|
59
|
+
- Decide on using a DSL or a web application for this purpose.
|
|
60
|
+
|
|
61
|
+
This summary should help guide the development and focus on the core objectives and future directions.
|
|
62
|
+
|
|
1
63
|
|
|
2
64
|
## Schema for AI Agents
|
|
3
65
|
|
data/package-lock.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "ad-agent_architecture",
|
|
3
|
-
"version": "0.0.
|
|
3
|
+
"version": "0.0.6",
|
|
4
4
|
"lockfileVersion": 3,
|
|
5
5
|
"requires": true,
|
|
6
6
|
"packages": {
|
|
7
7
|
"": {
|
|
8
8
|
"name": "ad-agent_architecture",
|
|
9
|
-
"version": "0.0.
|
|
9
|
+
"version": "0.0.6",
|
|
10
10
|
"devDependencies": {
|
|
11
11
|
"@klueless-js/semantic-release-rubygem": "github:klueless-js/semantic-release-rubygem",
|
|
12
12
|
"@semantic-release/changelog": "^6.0.3",
|
data/package.json
CHANGED