Project3/rag

.gitignore

@@ -190,4 +190,7 @@ project_podcast_summarizer/data/summaries/*.json
 project_podcast_summarizer/data/transcripts/mini.txt
 
 # fine tuning
-*.jsonl
+*.jsonl
+
+# Projects
+project_rag/app/index_store/*.json

project_rag/README.md

@@ -0,0 +1,41 @@
+## New Additions
+
+- Data Engineering Now Generates the Index Store
+- App now loads the index store
+- Chatbot Queries now operate with RAG
+
+## New Project Local Setup
+- cd into project_rag directory
+- Create new virtualenv and activate it
+- pip install -r requirements.txt
+- PYTHONPATH=../ python data_engineering/rag_index_generator.py  # note this uses the parent directory for PYTHONPATH
+
+If you get:
+```shell
+Traceback (most recent call last):
+  File "/PATH/TO/REPO/ai-engineering-course/project_rag/data_engineering/rag_index_generator.py", line 12, in <module>
+    from shared.settings import DATA_DIR, BASE_DIR
+ModuleNotFoundError: No module named 'shared'
+```
+It is because you have not appended the repo root directory to your PYTHONPATH environment variable
+
+## Code New Additions
+- RAG index generation (offline)
+- New endpoint with chat inference (online) (incl. new schema)
+- New chatbot template (online)
+- RAG capabilities for this endpoint (online + deps.py)
+- Split out config and New evar
+
+
+## Project Local Setup (Same as previous project)
+
+1. cd into project directory & create virtualenv & activate it
+2. `pip install -r requirements.txt`
+3. Run the DB migrations `PYTHONPATH=. python prestart.py` (only required once)
+4. Run the FastAPI server Python command: `PYTHONPATH=. python app/main.py`
+6. Open http://localhost:8001/
+
+
+## Troubleshooting
+`ModuleNotFoundError: No module named 'project_rag'` - means that you need to add the
+`project_rag` directory to your PYTHONPATH. 

project_rag/alembic.ini

@@ -0,0 +1,71 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = alembic
+
+# template used to generate migration files
+# file_template = %%(rev)s_%%(slug)s
+
+# timezone to use when rendering the date
+# within the migration file as well as the filename.
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+#truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; this defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path
+# version_locations = %(here)s/bar %(here)s/bat alembic/versions
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# Logging configuration
+[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

project_rag/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

project_rag/alembic/env.py

@@ -0,0 +1,91 @@
+from __future__ import with_statement
+from sqlalchemy.ext.asyncio import create_async_engine, AsyncEngine
+from sqlalchemy.engine import Connection
+import asyncio
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+from logging.config import fileConfig
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+# target_metadata = None
+
+from app.db.base_class import Base  # noqa
+from app.db.session import SQLALCHEMY_DATABASE_URI
+from app.models.podcast import Podcast, Episode, Summary
+
+target_metadata = Base.metadata
+
+
+def get_url():
+    return SQLALCHEMY_DATABASE_URI
+
+
+def run_migrations_offline():
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = get_url()
+    context.configure(
+        url=url, target_metadata=target_metadata, literal_binds=True, compare_type=True
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def do_run_migrations(connection: Connection) -> None:
+    context.configure(connection=connection, target_metadata=target_metadata)
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+async def run_async_migrations() -> None:
+    """In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    configuration = config.get_section(config.config_ini_section)
+    configuration["sqlalchemy.url"] = get_url()
+
+    # Using create_async_engine instead of engine_from_config
+    connectable: AsyncEngine = create_async_engine(
+        configuration["sqlalchemy.url"],
+        echo=True,
+    )
+
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+
+    await connectable.dispose()
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode."""
+
+    asyncio.run(run_async_migrations())
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

project_rag/alembic/script.py.mako

@@ -0,0 +1,24 @@
+"""${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 identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade():
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade():
+    ${downgrades if downgrades else "pass"}

project_rag/alembic/versions/728c3af72e3d_initial_tables.py

@@ -0,0 +1,51 @@
+"""initial tables
+
+Revision ID: 728c3af72e3d
+Revises: 
+Create Date: 2024-02-24 17:02:03.549236
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '728c3af72e3d'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('podcast',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('name', sa.String(length=255), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('episode',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('title', sa.String(length=255), nullable=False),
+    sa.Column('url', sa.String(length=512), nullable=True),
+    sa.Column('podcast_id', sa.Integer(), nullable=False),
+    sa.Column('transcript', sa.Text(), nullable=True),
+    sa.ForeignKeyConstraint(['podcast_id'], ['podcast.id'], ),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('summary',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('content', sa.Text(), nullable=True),
+    sa.Column('episode_id', sa.Integer(), nullable=True),
+    sa.ForeignKeyConstraint(['episode_id'], ['episode.id'], ),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('episode_id')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('summary')
+    op.drop_table('episode')
+    op.drop_table('podcast')
+    # ### end Alembic commands ###

project_rag/app/config.py

@@ -0,0 +1,56 @@
+import pathlib
+from typing import Optional
+
+from dotenv import load_dotenv
+from pydantic_settings import BaseSettings
+
+load_dotenv()
+
+# Project Directories
+ROOT: pathlib.Path = pathlib.Path(__file__).resolve().parent.parent
+PROMPT_DIR: pathlib.Path = ROOT / 'data_engineering' / 'prompts'
+TRANSCRIPT_DIR: pathlib.Path = ROOT / 'data' / 'transcripts'
+SUMMARY_DIR: pathlib.Path = ROOT / 'data' / 'summaries'
+MODEL_DIR: pathlib.Path = ROOT / 'data_engineering' / 'models'
+INDEX_DIR: pathlib.Path = ROOT / "app" / "index_store"
+
+class LLMSettings(BaseSettings):
+    """
+    Defines the settings for the Large Language Model (LLM).
+
+    Attributes:
+        CONTEXT_WINDOW (int): The context window size for the LLM.
+        N_GPU_LAYERS (int): The number of GPU layers to be used by the LLM.
+        MAX_TOKENS (int): The maximum number of tokens to be generated in one response.
+        TEMPERATURE (float): The temperature setting for the LLM's creativity in responses.
+        MODEL (str): The identifier for the LLM model to be used.
+        TOGETHER_API_KEY (str): The API key for accessing the LLM, expected to be loaded from the environment.
+    """
+    CONTEXT_WINDOW: int = 16000
+    N_GPU_LAYERS: int = 1
+    MAX_TOKENS: int = 512
+    TEMPERATURE: float = 0.8
+    MODEL: str = "mistralai/Mixtral-8x7B-Instruct-v0.1"
+    TOGETHER_API_KEY: str  # picked up from environment
+
+class Settings(BaseSettings):
+    """
+    Configuration settings for the application, including database and LLM configurations.
+
+    Attributes:
+        SQLALCHEMY_DATABASE_URI (Optional[str]): The database connection URI.
+        llm (LLMSettings): Nested settings for configuring the Large Language Model.
+    """
+    SQLALCHEMY_DATABASE_URI: Optional[str] = "sqlite:///example.db"
+    llm: LLMSettings = LLMSettings()
+
+    class Config:
+        """
+        Configuration class for settings.
+
+        Attributes:
+            case_sensitive (bool): Specifies if the configuration keys should be case-sensitive.
+        """
+        case_sensitive: bool = True
+
+settings: Settings = Settings()

project_rag/app/crud/__init__.py

@@ -0,0 +1 @@
+from .crud_podcast import podcast, episode, summary