Jfrost readme Updates plus Serdar's changes (#6)

* Resolved merge conflict in file

* remove secret key

* Integrate azure_ai and age enablement

* Add new related data and fix issues

* Add .env.sample file and make the options functional

* Fix Azure ML usage

* Fix venv related issue while running azd up

* First commit of combined branch of updated Readme.md and Serdar's Changes branch together

---------

Co-authored-by: Serdar Mumcu <[email protected]>

.devcontainer/devcontainer.json

@@ -0,0 +1,57 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the README at:
+// https://github.com/microsoft/vscode-dev-containers/tree/v0.245.0/containers/python-3
+{
+	"name": "legal-research-copilot-postgresql",
+	"dockerComposeFile": "../docker-compose.yaml",
+	"service": "app",
+	"workspaceFolder": "/workspace",
+	"forwardPorts": [5432],
+	"portsAttributes": {
+		"5432": {"label": "PostgreSQL port", "onAutoForward": "silent"},
+		"8000": {"label": "Backend port", "onAutoForward": "openBrowser"},
+		"5173": {"label": "Frontend port", "onAutoForward": "openBrowser"}
+	},
+    "features": {
+        "ghcr.io/devcontainers/features/node:1": {
+            "version": "18",
+            "nodeGypDependencies": false
+        },
+        "ghcr.io/azure/azure-dev/azd:latest": {
+			"version": "1.10.1"
+		},
+		"ghcr.io/devcontainers/features/azure-cli": {}
+    },
+	// Configure tool-specific properties.
+	"customizations": {
+		// Configure properties specific to VS Code.
+		"vscode": {
+			// Add the IDs of extensions you want installed when the container is created.
+			"extensions": [
+				"ms-python.python",
+				"ms-python.vscode-pylance",
+				"charliermarsh.ruff",
+				"mtxr.sqltools",
+				"mtxr.sqltools-driver-pg",
+				"ms-vscode.vscode-node-azure-pack",
+                "esbenp.prettier-vscode"
+			],
+			// Set *default* container specific settings.json values on container create.
+			"settings": {
+				"python.defaultInterpreterPath": "/usr/local/bin/python",
+				"python.testing.unittestEnabled": false,
+				"python.testing.pytestEnabled": false,
+				"[python]": {
+					"editor.formatOnSave": true,
+					"editor.codeActionsOnSave": {
+						"source.fixAll": "explicit"
+					},
+					"editor.defaultFormatter": "charliermarsh.ruff"
+				}
+			}
+		}
+	},
+	// Use 'postCreateCommand' to run commands after the container is created.
+	"postCreateCommand": "pip install -r requirements-dev.txt && pip install -e src/backend",
+	// Comment out to connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
+	"remoteUser": "vscode"
+}

.env.sample

@@ -0,0 +1,40 @@
+# Database Configuration
+POSTGRES_HOST=localhost
+POSTGRES_USERNAME=postgres
+POSTGRES_PASSWORD=postgres
+POSTGRES_DATABASE=postgres
+POSTGRES_SSL=disable
+
+# Workspace Path
+WORKSPACE=/workspace
+
+# PostgreSQL User Configuration
+POSTGRES_USER_ID=1000
+POSTGRES_USER_NAME=postgres
+POSTGRES_USER_SHELL=/bin/bash
+
+# PostgreSQL and pgenv Versions
+PGENV_VERSION=1.3.7
+PG_VERSION=16.4
+
+# OpenAI Configuration
+OPENAI_CHAT_HOST=azure
+OPENAI_EMBED_HOST=azure
+
+# Azure OpenAI Configuration
+AZURE_OPENAI_ENDPOINT=https://serdar-azure-open-ai.openai.azure.com
+AZURE_OPENAI_VERSION=2024-08-01-preview
+AZURE_OPENAI_CHAT_DEPLOYMENT=gpt-4o
+AZURE_OPENAI_CHAT_MODEL=gpt-4o
+AZURE_OPENAI_EMBED_DEPLOYMENT=text-embedding-3-small
+AZURE_OPENAI_EMBED_MODEL=text-embedding-3-small
+AZURE_OPENAI_EMBED_DIMENSIONS=1536
+AZURE_OPENAI_EMBEDDING_COLUMN=description_vector
+AZURE_OPENAI_EVAL_DEPLOYMENT=gpt-4
+AZURE_OPENAI_EVAL_MODEL=gpt-4
+AZURE_TENANT_ID=
+AZURE_OPENAI_KEY=YOUR-AZURE-OPENAI-API-KEY
+
+# Azure ML Configuration
+AZURE_ML_SCORING_ENDPOINT=https://mlukrerankeraml-bgev2m3.southcentralus.inference.ml.azure.com/score
+AZURE_ML_ENDPOINT_KEY=YOUR-AZURE-ML-ENDPOINT-KEY

.gitignore

@@ -6,3 +6,8 @@ Data_ingestion/.env
 Data_ingestion/.ipynb_checkpoints
 /src/frontend/node_modules/
 */package-lock.json
+.azure
+__pycache__/
+*.js.map
+*.pyc
+src/backend/static/assets/*

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "vendor/age"]
+	path = vendor/age
+	url = https://github.com/apache/age.git

Data_ingestion/poetry.toml

@@ -0,0 +1,2 @@
+[virtualenvs]
+create = true

Data_ingestion/pyproject.toml

@@ -0,0 +1,29 @@
+[tool.poetry]
+name = "data-ingestion"
+version = "0.1.0"
+description = ""
+authors = ["Your Name <[email protected]>"]
+license = "MIT"
+readme = "README.md"
+package-mode = false
+
+[tool.poetry.dependencies]
+python = ">=3.11,<3.13"
+graspologic = "^3.4.1"
+jupyter = "^1.1.1"
+pandas = "^2.2.3"
+openai = "0.28.0"
+future = "^1.0.0"
+ipykernel = "^6.29.5"
+psycopg2 = "^2.9.10"
+python-dotenv = "^1.0.1"
+
+[tool.poetry.group.dev.dependencies]
+black = "*"
+ipywidgets = "*"
+isort = "*"
+pylint = "*"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"