2815 launch app with persist

.github/workflows/python-CI.yml

@@ -2,7 +2,7 @@ name: Python CI
 
 on:
     push:
-        branches: [main]
+        branches: [main, sql]
     pull_request:
         paths:
             - "src/**"

Dockerfile

@@ -36,7 +36,7 @@ COPY ./ /phoenix/
 COPY --from=frontend-builder /phoenix/src/phoenix/server/static/ /phoenix/src/phoenix/server/static/
 # Delete symbolic links used during development.
 RUN find src/ -xtype l -delete  
-RUN pip install --target ./env .[container]
+RUN pip install --target ./env ".[container, pg]"
 
 # The production image is distroless, meaning that it is a minimal image that
 # contains only the necessary dependencies to run the application. This is

app/schema.graphql

@@ -543,11 +543,11 @@ type Project implements Node {
   endTime: DateTime
   recordCount(timeRange: TimeRange): Int!
   traceCount(timeRange: TimeRange): Int!
-  tokenCountTotal: Int!
+  tokenCountTotal(timeRange: TimeRange): Int!
   latencyMsP50: Float
   latencyMsP99: Float
   trace(traceId: ID!): Trace
-  spans(timeRange: TimeRange, traceIds: [ID!], first: Int = 50, last: Int, after: String, before: String, sort: SpanSort, rootSpansOnly: Boolean, filterCondition: String): SpanConnection!
+  spans(timeRange: TimeRange, first: Int = 50, last: Int, after: String, before: String, sort: SpanSort, rootSpansOnly: Boolean, filterCondition: String): SpanConnection!
 
   """
   Names of all available evaluations for traces. (The list contains no duplicates.)

cspell.json

@@ -37,6 +37,8 @@
         "respx",
         "rgba",
         "seafoam",
+        "sqlalchemy",
+        "Starlette",
         "templating",
         "tensorboard",
         "testset",

pyproject.toml

@@ -50,6 +50,9 @@ dependencies = [
   "openinference-instrumentation-langchain>=0.1.12",
   "openinference-instrumentation-llama-index>=1.2.0",
   "openinference-instrumentation-openai>=0.1.4",
+  "sqlalchemy>=2, <3",
+  "alembic>=1.3.0, <2",
+  "aiosqlite",
 ]
 dynamic = ["version"]
 
@@ -86,6 +89,11 @@ llama-index = [
   "llama-index-callbacks-arize-phoenix>=0.1.2",
   "openinference-instrumentation-llama-index>=1.2.0",
 ]
+
+pg = [
+  "asyncpg",
+]
+
 container = [
   "prometheus-client",
 ]

src/phoenix/__init__.py

@@ -9,7 +9,14 @@
 from .datasets.schema import EmbeddingColumnNames, RetrievalEmbeddingColumnNames, Schema
 from .session.client import Client
 from .session.evaluation import log_evaluations
-from .session.session import NotebookEnvironment, Session, active_session, close_app, launch_app
+from .session.session import (
+    NotebookEnvironment,
+    Session,
+    active_session,
+    close_app,
+    launch_app,
+    reset_all,
+)
 from .trace.fixtures import load_example_traces
 from .trace.trace_dataset import TraceDataset
 from .version import __version__
@@ -41,6 +48,7 @@
     "active_session",
     "close_app",
     "launch_app",
+    "reset_all",
     "Session",
     "load_example_traces",
     "TraceDataset",

src/phoenix/config.py

@@ -22,6 +22,10 @@
 """
 The project name to use when logging traces and evals. defaults to 'default'.
 """
+ENV_PHOENIX_SQL_DATABASE = "__DANGEROUS__PHOENIX_SQL_DATABASE"
+"""
+The database URL to use when logging traces and evals.
+"""
 ENV_SPAN_STORAGE_TYPE = "__DANGEROUS__PHOENIX_SPAN_STORAGE_TYPE"
 """
 **EXPERIMENTAL**
@@ -152,6 +156,14 @@ def get_env_span_storage_type() -> Optional["SpanStorageType"]:
         )
 
 
+def get_env_database_connection_str() -> str:
+    env_url = os.getenv(ENV_PHOENIX_SQL_DATABASE)
+    if env_url is None:
+        working_dir = get_working_dir()
+        return f"sqlite:///{working_dir}/phoenix.db"
+    return env_url
+
+
 class SpanStorageType(Enum):
     TEXT_FILES = "text-files"
 

src/phoenix/db/__init__.py

@@ -0,0 +1,3 @@
+from .migrate import migrate
+
+__all__ = ["migrate"]

src/phoenix/db/alembic.ini

@@ -0,0 +1,119 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Note this is overridden in .migrate during programatic migrations
+script_location = migrations
+
+# 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>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# 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 migrations/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:migrations/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.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# NB: This is commented out intentionally as it is dynamic
+# See migrations/env.py
+# sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[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
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix 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 = WARN
+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