feat: scaffold open source monorepo (v1 MVP)

.env.example

@@ -0,0 +1,34 @@
+# Database
+DATABASE_URL=postgresql://chatintel:chatintel@postgres:5432/chatintel
+
+# Auth
+JWT_SECRET=change-me-in-production-use-a-long-random-string
+JWT_ALGORITHM=HS256
+JWT_EXPIRE_MINUTES=10080
+
+# LLM (for evaluation and auto-labeling)
+# Set one of these based on your provider
+OPENAI_API_KEY=
+ANTHROPIC_API_KEY=
+GOOGLE_API_KEY=
+# LiteLLM model string, e.g. "gpt-4o-mini", "claude-3-5-haiku-20241022", "gemini/gemini-2.0-flash"
+DEFAULT_LLM_MODEL=gpt-4o-mini
+
+# File storage
+# "local" uses ./uploads dir; "s3" uses MinIO/S3
+STORAGE_BACKEND=local
+STORAGE_LOCAL_PATH=/app/uploads
+# MinIO/S3 (only needed if STORAGE_BACKEND=s3)
+S3_ENDPOINT_URL=http://minio:9000
+S3_BUCKET_NAME=chatintel
+S3_ACCESS_KEY=minioadmin
+S3_SECRET_KEY=minioadmin
+
+# Redis (Celery broker)
+REDIS_URL=redis://redis:6379/0
+
+# CORS
+ALLOWED_ORIGINS=http://localhost:5173,http://localhost:3000
+
+# Web
+VITE_API_BASE_URL=http://localhost:8000

.gitignore

@@ -0,0 +1,13 @@
+.env
+.DS_Store
+__pycache__/
+*.pyc
+*.pyo
+.pytest_cache/
+.venv/
+venv/
+node_modules/
+dist/
+.next/
+uploads/
+*.log

README.md

@@ -1,2 +1,71 @@
 # chatintel
-Open source Evaluation & Observability platform
+
+Open source conversation intelligence platform. Upload customer chat logs, analyze sentiment and metrics, and run LLM-as-judge evaluations — all self-hosted.
+
+## Features
+
+- **Ingestion** — upload CSV, JSON, or JSONL conversation files
+- **Conversations** — browse, search, and filter your data
+- **Dashboard** — metrics over time with label breakdowns
+- **Labels** — tag and categorise conversations
+- **Evaluations** — LLM-as-judge scoring (helpfulness, tone, resolution, clarity)
+
+## Quick start
+
+```bash
+cp .env.example .env
+# Edit .env — set JWT_SECRET and at least one LLM API key
+docker compose up
+```
+
+Open http://localhost:3000, create an account, and upload your first file.
+
+## Data format
+
+ChatIntel accepts any CSV or JSON file with conversation data. Minimum required fields:
+
+| Field | Description |
+|---|---|
+| `conversation_id` | Unique ID for the conversation |
+| `role` | Message sender: `user` or `assistant` |
+| `content` | Message text |
+
+Optional fields: `user_id`, `platform`, `status`, `sentiment`, `satisfaction_score`, `start_time`, `end_time`.
+
+## Configuration
+
+| Variable | Description |
+|---|---|
+| `JWT_SECRET` | Secret for signing auth tokens (required) |
+| `DEFAULT_LLM_MODEL` | LiteLLM model string, e.g. `gpt-4o-mini` |
+| `OPENAI_API_KEY` | OpenAI key for evaluations |
+| `ANTHROPIC_API_KEY` | Anthropic key for evaluations |
+| `GOOGLE_API_KEY` | Google key for evaluations |
+| `STORAGE_BACKEND` | `local` (default) or `s3` |
+
+## Development
+
+```bash
+# API
+cd api && pip install -r requirements.txt
+cp ../.env.example .env
+alembic upgrade head
+uvicorn chatintel.main:app --reload
+
+# Web
+cd web && npm install
+npm run dev
+```
+
+## Architecture
+
+```
+web/     React + Vite + shadcn/ui
+api/     FastAPI + SQLAlchemy + PostgreSQL
+```
+
+Background file processing runs via Celery workers. No cloud dependencies required.
+
+## License
+
+Apache 2.0

api/Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y libpq-dev gcc && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+RUN mkdir -p /app/uploads

api/alembic.ini

@@ -0,0 +1,38 @@
+[alembic]
+script_location = alembic
+prepend_sys_path = .
+sqlalchemy.url = postgresql://chatintel:chatintel@postgres:5432/chatintel
+
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

api/alembic/env.py

@@ -0,0 +1,42 @@
+import os
+from logging.config import fileConfig
+from sqlalchemy import engine_from_config, pool
+from alembic import context
+
+config = context.config
+
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# Override sqlalchemy.url from env if present
+db_url = os.environ.get("DATABASE_URL")
+if db_url:
+    config.set_main_option("sqlalchemy.url", db_url)
+
+from chatintel.database import Base
+target_metadata = Base.metadata
+
+
+def run_migrations_offline():
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(url=url, target_metadata=target_metadata, literal_binds=True)
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

api/alembic/script.py.mako

@@ -0,0 +1,23 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

api/alembic/versions/0001_initial.py

@@ -0,0 +1,105 @@
+"""initial schema
+
+Revision ID: 0001
+Revises:
+Create Date: 2025-01-01 00:00:00
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects.postgresql import UUID, JSONB
+
+revision = "0001"
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "users",
+        sa.Column("id", UUID(as_uuid=False), primary_key=True),
+        sa.Column("email", sa.String(), nullable=False, unique=True),
+        sa.Column("password_hash", sa.String(), nullable=False),
+        sa.Column("full_name", sa.String()),
+        sa.Column("is_admin", sa.Boolean(), nullable=False, server_default="false"),
+        sa.Column("is_enabled", sa.Boolean(), nullable=False, server_default="true"),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+    )
+    op.create_index("ix_users_email", "users", ["email"])
+
+    op.create_table(
+        "data_sources",
+        sa.Column("id", UUID(as_uuid=False), primary_key=True),
+        sa.Column("user_id", UUID(as_uuid=False), sa.ForeignKey("users.id", ondelete="CASCADE"), nullable=False),
+        sa.Column("filename", sa.String(), nullable=False),
+        sa.Column("file_path", sa.String(), nullable=False),
+        sa.Column("file_type", sa.String(), nullable=False),
+        sa.Column("status", sa.String(), nullable=False, server_default="pending"),
+        sa.Column("row_count", sa.Integer()),
+        sa.Column("error_message", sa.Text()),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+    )
+
+    op.create_table(
+        "conversations",
+        sa.Column("id", UUID(as_uuid=False), primary_key=True),
+        sa.Column("user_id", UUID(as_uuid=False), sa.ForeignKey("users.id", ondelete="CASCADE"), nullable=False),
+        sa.Column("conversation_id", sa.String(), nullable=False),
+        sa.Column("external_user_id", sa.String()),
+        sa.Column("messages", JSONB()),
+        sa.Column("status", sa.String()),
+        sa.Column("platform", sa.String()),
+        sa.Column("sentiment", sa.String()),
+        sa.Column("satisfaction_score", sa.Numeric()),
+        sa.Column("message_count", sa.Integer()),
+        sa.Column("start_time", sa.DateTime(timezone=True)),
+        sa.Column("end_time", sa.DateTime(timezone=True)),
+        sa.Column("duration_seconds", sa.Numeric()),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+        sa.UniqueConstraint("user_id", "conversation_id", name="uq_conversations_user_conv"),
+    )
+    op.create_index("ix_conversations_user_id", "conversations", ["user_id"])
+    op.create_index("ix_conversations_end_time", "conversations", ["end_time"])
+
+    op.create_table(
+        "labels",
+        sa.Column("id", UUID(as_uuid=False), primary_key=True),
+        sa.Column("user_id", UUID(as_uuid=False), sa.ForeignKey("users.id", ondelete="CASCADE"), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("description", sa.Text()),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+        sa.UniqueConstraint("user_id", "name", name="uq_labels_user_name"),
+    )
+
+    op.create_table(
+        "conversation_labels",
+        sa.Column("conversation_id", UUID(as_uuid=False), sa.ForeignKey("conversations.id", ondelete="CASCADE"), primary_key=True),
+        sa.Column("label_id", UUID(as_uuid=False), sa.ForeignKey("labels.id", ondelete="CASCADE"), primary_key=True),
+        sa.Column("classified_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+    )
+
+    op.create_table(
+        "evaluations",
+        sa.Column("id", UUID(as_uuid=False), primary_key=True),
+        sa.Column("conversation_id", UUID(as_uuid=False), sa.ForeignKey("conversations.id", ondelete="CASCADE"), nullable=False),
+        sa.Column("user_id", UUID(as_uuid=False), sa.ForeignKey("users.id", ondelete="CASCADE"), nullable=False),
+        sa.Column("evaluator_model", sa.String(), nullable=False),
+        sa.Column("criteria", sa.String(), nullable=False),
+        sa.Column("score", sa.Numeric()),
+        sa.Column("reasoning", sa.Text()),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.text("NOW()")),
+    )
+    op.create_index("ix_evaluations_conversation_id", "evaluations", ["conversation_id"])
+
+
+def downgrade() -> None:
+    op.drop_table("evaluations")
+    op.drop_table("conversation_labels")
+    op.drop_table("labels")
+    op.drop_table("conversations")
+    op.drop_table("data_sources")
+    op.drop_table("users")

api/chatintel/auth.py

@@ -0,0 +1,35 @@
+from datetime import datetime, timedelta, timezone
+from typing import Optional
+
+from jose import jwt, JWTError
+from passlib.context import CryptContext
+
+from .config import settings
+
+pwd_context = CryptContext(schemes=["bcrypt"], deprecated="auto")
+
+
+def hash_password(password: str) -> str:
+    return pwd_context.hash(password)
+
+
+def verify_password(plain: str, hashed: str) -> bool:
+    return pwd_context.verify(plain, hashed)
+
+
+def create_access_token(user_id: str, email: str, is_admin: bool) -> str:
+    expire = datetime.now(timezone.utc) + timedelta(minutes=settings.jwt_expire_minutes)
+    payload = {
+        "sub": user_id,
+        "email": email,
+        "is_admin": is_admin,
+        "exp": expire,
+    }
+    return jwt.encode(payload, settings.jwt_secret, algorithm=settings.jwt_algorithm)
+
+
+def decode_token(token: str) -> Optional[dict]:
+    try:
+        return jwt.decode(token, settings.jwt_secret, algorithms=[settings.jwt_algorithm])
+    except JWTError:
+        return None