Added database to inference server (#1446)

* added db for inference

* fixed dockerfiles for inference

docker-compose.yaml

@@ -136,6 +136,23 @@ services:
       - "3000:3000"
     command: bash wait-for-postgres.sh node server.js
 
+  # This DB is for Inference
+  inference-db:
+    image: postgres
+    restart: always
+    ports:
+      - 5434:5432
+    environment:
+      POSTGRES_USER: postgres
+      POSTGRES_PASSWORD: postgres
+      POSTGRES_DB: oasst_inference
+    healthcheck:
+      test: ["CMD", "pg_isready", "-U", "postgres"]
+      interval: 2s
+      timeout: 2s
+      retries: 10
+    profiles: ["inference"]
+
   inference-server:
     build:
       dockerfile: docker/inference/Dockerfile.server
@@ -145,13 +162,25 @@ services:
     environment:
       - "PORT=8000"
       - "REDIS_HOST=redis"
+      - POSTGRES_HOST=inference-db
+      - POSTGRES_DB=oasst_inference
     volumes:
       - "./oasst-shared:/opt/inference/lib/oasst-shared"
       - "./inference/server:/opt/inference/server"
     restart: unless-stopped
+    ports:
+      - "8000:8000"
     depends_on:
       redis:
         condition: service_healthy
+      inference-db:
+        condition: service_healthy
+    profiles: ["inference"]
+
+  inference-text-generation-server:
+    image: ghcr.io/huggingface/text-generation-inference
+    environment:
+      - "MODEL_ID=distilgpt2"
     profiles: ["inference"]
 
   inference-worker:
@@ -167,29 +196,7 @@ services:
       - "./oasst-shared:/opt/inference/lib/oasst-shared"
       - "./inference/worker:/opt/inference/worker"
     depends_on:
-      - inference-server
+      - inference-text-generation-server
     deploy:
       replicas: 1
     profiles: ["inference"]
-
-  inference-text-client:
-    build:
-      dockerfile: docker/inference/Dockerfile.text-client
-      context: .
-    image: oasst-inference-text-client
-    environment:
-      - "BACKEND_URL=http://inference-server:8000"
-    tty: true
-    stdin_open: true
-    volumes:
-      - "./inference/worker:/opt/inference/worker"
-    restart: unless-stopped
-    depends_on:
-      - inference-server
-    profiles: ["inference"]
-
-  inference-text-generation-server:
-    image: ghcr.io/huggingface/text-generation-inference
-    environment:
-      - "MODEL_ID=distilgpt2"
-    profiles: ["inference"]

docker/inference/Dockerfile.server

@@ -7,7 +7,7 @@ ARG APP_USER="${MODULE}-${SERVICE}"
 ARG APP_RELATIVE_PATH="${MODULE}/${SERVICE}"
 
 
-FROM python:3-slim as build
+FROM python:3.10-slim as build
 ARG APP_RELATIVE_PATH
 
 WORKDIR /build
@@ -22,7 +22,7 @@ RUN --mount=type=cache,target=/var/cache/pip \
 
 
 
-FROM python:3.10-alpine3.17 as base-env
+FROM python:3.10-slim as base-env
 ARG APP_USER
 ARG APP_RELATIVE_PATH
 ARG MODULE
@@ -50,6 +50,9 @@ WORKDIR ${APP_ROOT}
 
 
 COPY --chown="${APP_USER}:${APP_USER}" --from=build /build/lib                     ${APP_LIBS}
+COPY --chown="${APP_USER}:${APP_USER}"              ./${APP_RELATIVE_PATH}/alembic alembic
+COPY --chown="${APP_USER}:${APP_USER}"              ./${APP_RELATIVE_PATH}/alembic.ini .
+COPY --chown="${APP_USER}:${APP_USER}"              ./${APP_RELATIVE_PATH}/oasst_inference_server oasst_inference_server
 COPY --chown="${APP_USER}:${APP_USER}"              ./${APP_RELATIVE_PATH}/main.py .
 
 

docker/inference/Dockerfile.worker

@@ -48,7 +48,7 @@ WORKDIR ${APP_ROOT}
 
 
 COPY --chown="${APP_USER}:${APP_USER}" --from=build /build/lib                         ${APP_LIBS}
-COPY --chown="${APP_USER}:${APP_USER}"              ./${APP_RELATIVE_PATH}/__main__.py .
+COPY --chown="${APP_USER}:${APP_USER}"              ./${APP_RELATIVE_PATH}/*.py .
 
 
 CMD python3 __main__.py --backend-url "${BACKEND_URL}" --inference-server-url "${INFERENCE_SERVER_URL}"

inference/full-dev-setup.sh

@@ -3,9 +3,11 @@
 # Creates a tmux window with splits for the individual services
 
 tmux new-session -d -s "inference-dev-setup"
-tmux send-keys "docker run --rm -it -p 6379:6379 redis" C-m
+tmux send-keys "docker run --rm -it -p 5432:5432 -e POSTGRES_PASSWORD=postgres --name postgres postgres" C-m
 tmux split-window -h
-tmux send-keys "docker run --rm -it -p 8001:80 -e MODEL_ID=distilgpt2 ghcr.io/huggingface/text-generation-inference" C-m
+tmux send-keys "docker run --rm -it -p 6379:6379 --name redis redis" C-m
+tmux split-window -h
+tmux send-keys "docker run --rm -it -p 8001:80 -e MODEL_ID=distilgpt2 -v $HOME/.cache/huggingface:/root/.cache/huggingface --name text-generation-inference ghcr.io/huggingface/text-generation-inference" C-m
 tmux split-window -h
 tmux send-keys "cd server" C-m
 tmux send-keys "uvicorn main:app --reload" C-m

inference/server/alembic.ini

@@ -0,0 +1,105 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = %(here)s/alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# 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.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# sqlalchemy.url = postgresql://<username>:<password>@<host>/<database_name>
+sqlalchemy.url = postgresql://postgres:postgres@localhost:5432/postgres
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+hooks = black
+black.type = console_scripts
+black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# 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

inference/server/alembic/README

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

inference/server/alembic/env.py

@@ -0,0 +1,78 @@
+from logging.config import fileConfig
+
+import sqlmodel
+from alembic import context
+from oasst_inference_server import models  # noqa: F401
+from sqlalchemy import engine_from_config, pool
+
+# 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.
+if config.config_file_name is not None:
+    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 = sqlmodel.SQLModel.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """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 = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    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.get_context()._ensure_version_table()
+            connection.execute("LOCK TABLE alembic_version IN ACCESS EXCLUSIVE MODE")
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

inference/server/alembic/script.py.mako

@@ -0,0 +1,25 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel
+${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() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}