feat(upload): first working version

Author: Mte90

.env.example

@@ -0,0 +1,32 @@
+# Example .env for Local Codebase Analyzer
+# Copy to .env and edit values
+
+# Local repo to analyze
+LOCAL_PATH=/path/to/your/local/repo
+
+# Optional: path to virtualenv (if provided)
+VENV_PATH=/path/to/your/.venv
+
+# External OpenAI-compatible endpoints (or leave blank to rely on env)
+API_URL=https://api.regolo.ai/v1/
+
+# API key to use with the external endpoints
+API_KEY=sk-REPLACE_ME
+
+# SQLite DB path
+DATABASE_PATH=codebase.db
+
+# Max file size (bytes) to index / embed
+MAX_FILE_SIZE=200000
+
+# Models: set the model names / identifiers your provider expects
+# e.g. for embeddings: text-embedding-3-small or other provider model id
+EMBEDDING_MODEL=text-embedding-3-small
+
+# Model used for coding / generation (provider model id)
+CODING_MODEL=gpt-4o-code-preview
+
+# Uvicorn server configuration
+# Host (default 127.0.0.1) and port (default 8000) used when launching uvicorn
+UVICORN_HOST=127.0.0.1
+UVICORN_PORT=8080

.gitignore

@@ -0,0 +1,6 @@
+.env
+.venv
+codebase.*
+picocode.egg-info
+uv.lock
+__pycache__

README.md

@@ -1,6 +1,6 @@
 [![License](https://img.shields.io/badge/License-GPL%20v3-blue.svg)](http://www.gnu.org/licenses/gpl-3.0)   
 ```markdown
-# PicoCode - Local Codebase Analyzer
+# PicoCode - Local Codebase Assistant
 
 Are you looking for a simple way to asks question to your codebase using the inference provider you want without to be locked to a specific service?
 This tool is a way to achieve this!