[119] Architecture diagram (#135)

.python-version

@@ -0,0 +1 @@
+3.11.7

README.md

@@ -1,10 +1,11 @@
 # labs
 
-<a target="_blank" href="https://cookiecutter-data-science.drivendata.org/">
-    <img src="https://img.shields.io/badge/CCDS-Project%20template-328F97?logo=cookiecutter" />
-</a>
+<img src="https://img.shields.io/badge/runtime_revolution-labs-blue" />
 
-Runtime Labs
+## Topics
+
+- [Architecture](docs/rag.md)
+- [R&D](docs/rd.md)
 
 ## Getting Started
 
@@ -38,9 +39,3 @@ Here's the steps to setup the project locally:
 3. `make up`
 4. `make api` or `ENV=local make api`
 5. `ENV=test make tests`
-
-
-## Approaches, Tests Conducted and Results
-
-For details on the approaches and tests conducted on issues encountered during development, 
-refer to the document [here](./doc/results.md)

docker-compose.yml

@@ -1,4 +1,12 @@
 services:
+  postgres:
+    container_name: postgres
+    image: postgres:13
+    environment:
+      POSTGRES_USER: ${DATABASE_USER}
+      POSTGRES_PASSWORD: ${DATABASE_PASS}
+      POSTGRES_DB: ${POSTGRES_DB}
+
   labs-db:
     container_name: labs-db
     image: pgvector/pgvector:pg16

doc/diagram/class_diagram_script.py → docs/diagram/class_diagram_script.py

@@ -28,7 +28,9 @@ def extract_classes(file_path):
                             args.append(f"{arg.arg}: {arg.annotation.id}")
                         elif isinstance(arg.annotation, ast.Subscript):
                             if isinstance(arg.annotation.value, ast.Name):
-                                args.append(f"{arg.arg}: {arg.annotation.value.id}[{arg.annotation.slice.value.id}]")
+                                args.append(
+                                    f"{arg.arg}: {arg.annotation.value.id}[{arg.annotation.slice.value.id}]"
+                                )
                         else:
                             args.append(arg.arg)
                     method_signature = f"{visibility} {method_name}({', '.join(args)})"

docs/rag.md

@@ -0,0 +1,68 @@
+# RAG Architecture
+
+## Challenges
+
+1. Context embeddings creation
+
+    * how are embeddings created? which strategy was used?
+
+2. Query + context
+
+    * Ensure query + context reflect what's intended
+    * provides an acceptable answer
+
+3. Include the generated answer in the correct place in the project
+
+## RAG General view
+
+```mermaid
+flowchart
+    
+    subgraph Prompt
+        A[/Query/] --> B[Embedding model<br> <strong>text-embedding-ada-002</strong>]
+        B --> C[Embeddings]
+    end
+    subgraph Context
+        E[/Data source/] --> F[Embedding model<br> <strong>text-embedding-ada-002</strong>]
+        F --> G[Embeddings]
+    end
+    subgraph Vector Database
+        C --> D[(<strong>PostgreSQL PGVector</strong>)]
+        G --> D
+    end
+    subgraph LLM
+        A --> H[/Query + Context/]
+        D --> H
+        H --> I[OpenAPI o1]
+        I --> J[/Response/]
+    end
+```
+
+## Integrations
+
+```mermaid
+flowchart
+    subgraph CodeMonkey
+        API
+    end
+
+    subgraph Local
+        C[Repository]
+    end
+
+    subgraph Github
+        D[Repository]
+        Issues
+        App
+    end
+
+    Github <--> CodeMonkey
+    Local <--> CodeMonkey
+```
+
+## Embeddings and LLM
+
+| Embeddings | LLM |
+| --- | --- |
+| text-embedding-ada-002 | OpenAPI o1 | 
+| text-embedding-ada-002 | Llama 3.2 (local) | 

doc/results.md → docs/rd.md

@@ -1,10 +1,10 @@
-# Project tests results
+# Research & Development
 
 This document aims to document some of the approaches tested and the discoveries made on various problems, 
 as well as the results achieved from the tests conducted.
 
 
-## Embeddins
+## Embeddings
 
 During the course of the project, various approaches were taken regarding how embeddings are generated, namely: