Document parsing module

.github/workflows/ci.yml

@@ -52,7 +52,7 @@ jobs:
 
       # Step 7: Upload Coverage Report as an Artifact (optional)
       - name: Upload Coverage Report
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: coverage-report
           path: htmlcov/

.gitignore

@@ -1,3 +1,4 @@
+project_data/
 .python-version
 .vscode/
 .DS_Store

pyproject.toml

@@ -1,21 +1,34 @@
+[tool.poetry.scripts]
+sequestrae = "sequestrae_engine.cli.main:main"
+
 [tool.poetry]
 name = "sequestrae-engine"
 version = "0.1.0"
-description = "A Biochar Carbon Removal Assessment Engine for evaluating carbon sequestration potential."
+description = "A Biochar Carbon Removal Assessment Engine for evaluating project risk."
 authors = ["Du Phan <du-phan@users.noreply.github.com>"]
 license = "MIT"
 readme = "README.md"
 homepage = "https://github.com/du-phan/sequestrae-engine"
 repository = "https://github.com/du-phan/sequestrae-engine"
 keywords = ["biochar", "carbon removal", "assessment", "engine", "sequestration"]
+packages = [
+    { include = "sequestrae_engine" }
+]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<4.0"
 numpy = ">=1.24,<2.0"
 pandas = "^2.0"
-pydantic = "^1.10.2"
+pydantic = "^2.5.2"
 jsonschema = "^4.16.0"
 jupyterlab = "^4.0.5"
+llama-index = "^0.12.16"
+llama-parse = "^0.6"
+python-dotenv = "^1.0.0"
+openai = "^1.0.0"
+mistralai = "^1.3"
+google-genai = "^1.0.0"
+supabase = "^2.10.0"
 
 [tool.poetry.dev-dependencies]
 black = "24.10.0"