nucliadb-agentic-api 1.0.0.post156__tar.gz

nucliadb_agentic_api-1.0.0.post156/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.4
+Name: nucliadb_agentic_api
+Version: 1.0.0.post156
+Summary: NucliaDB Agentic API for Hyperforge
+Author: AI Data Team
+Author-email: AI Data Team <learning@nuclia.com>
+License-Expression: Apache-2.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Project-URL: Progress, https://progress.com
+Project-URL: Github, https://github.com/nuclia/forge
+Project-URL: API Reference, https://docs.rag.progress.cloud
+Description-Content-Type: text/markdown
+
+# NucliaDB Agentic API
+
+The NucliaDB Agentic API package exposes NucliaDB-oriented agentic capabilities
+for Hyperforge, including ASK/search flows and MCP integrations.
+
+## Install
+
+From the workspace root:
+
+```bash
+uv sync
+```
+
+## Run
+
+Start the service:
+
+```bash
+uv run nucliadb-agentic-api
+```
+
+Useful endpoints:
+
+- `/health/ready`
+- `/health/alive`
+- `/metrics`
+
+## Configuration
+
+Runtime configuration is provided through environment variables consumed by
+Pydantic settings. Common settings include:
+
+- `HTTP_HOST` and `HTTP_PORT`
+- `MEMORY_READER_NUCLIADB`, `MEMORY_WRITER_NUCLIADB`, and
+  `MEMORY_SEARCH_NUCLIADB`
+- `MEMORY_APIKEY_NUCLIADB`
+- `VALKEY_URL`
+- `IDP_REGIONAL_GRPC`
+- `LOAD_MODULES`
+
+## Development
+
+Run the package tests from the workspace root:
+
+```bash
+make test
+```
+
+
+# Objective
+Enhance the RAG experience by offering RAO features directly in a KB.
+
+# How?
+The same way we store search configs in the KB, we could store agentic configs, and when calling the `/ask` endpoint we can refer to a given agentic config.
+
+# Scope
+
+The corresponding RAO workflow will be:
+- a Rephrase (optionally)
+- a SmartAgent
+- a Summarize
+
+Possible sources for the SmartAgent:
+- The current KB (possibly several times with different filters)
+- Sync service (using connections defined in the current KB)
+- Google
+- Perplexity
+- MCP
+
+Out of scope
+- Other KBs
+- SQL
+- Snowflake (?)
+- Sitefinity (?)
+
+# Config spec
+
+```json
+{
+  "rephrase": { // optional
+    "ask_to": <filter_expression>, //optional
+    "prompt": <string>, // optional
+    "model": <model>, // optional
+  },
+  "smart_agent": {
+    "mode": <reactive | plan_execute>,
+    "extra_prompt": <string>, // optional
+    "models": { // optional
+      "context_validation": <model>, // optional
+      "planner": <model>, // optional
+      "executor": <model>, // optional
+    },
+    "sources": [<source list>]
+  },
+  "summarize": { // optional
+    "user_prompt": <string>, // optional
+    "system_prompt": <string>, // optional
+    "conversational": <boolean>,
+    "model": <model>, // optional
+    // and citations must be forced to chunk-level
+  }
+}
+```
+
+And sources can be:
+
+```json
+{
+  "type": "nucliadb",
+  "description": <string>,
+  "filter_expression": <filter_expression>, //optional
+}
+
+{
+  "type": "sync",
+  "description": <string>,
+  "connection": <connection_id>
+}
+
+{
+  "type": "google",
+  "description": <string>
+}
+
+{
+  "type": "perplexity",
+  "description": <string>
+}
+
+{
+  "type": "mcp",
+  "description": <string>,
+  <...the MCP driver params>
+}
+````

nucliadb_agentic_api-1.0.0.post156/README.md

@@ -0,0 +1,135 @@
+# NucliaDB Agentic API
+
+The NucliaDB Agentic API package exposes NucliaDB-oriented agentic capabilities
+for Hyperforge, including ASK/search flows and MCP integrations.
+
+## Install
+
+From the workspace root:
+
+```bash
+uv sync
+```
+
+## Run
+
+Start the service:
+
+```bash
+uv run nucliadb-agentic-api
+```
+
+Useful endpoints:
+
+- `/health/ready`
+- `/health/alive`
+- `/metrics`
+
+## Configuration
+
+Runtime configuration is provided through environment variables consumed by
+Pydantic settings. Common settings include:
+
+- `HTTP_HOST` and `HTTP_PORT`
+- `MEMORY_READER_NUCLIADB`, `MEMORY_WRITER_NUCLIADB`, and
+  `MEMORY_SEARCH_NUCLIADB`
+- `MEMORY_APIKEY_NUCLIADB`
+- `VALKEY_URL`
+- `IDP_REGIONAL_GRPC`
+- `LOAD_MODULES`
+
+## Development
+
+Run the package tests from the workspace root:
+
+```bash
+make test
+```
+
+
+# Objective
+Enhance the RAG experience by offering RAO features directly in a KB.
+
+# How?
+The same way we store search configs in the KB, we could store agentic configs, and when calling the `/ask` endpoint we can refer to a given agentic config.
+
+# Scope
+
+The corresponding RAO workflow will be:
+- a Rephrase (optionally)
+- a SmartAgent
+- a Summarize
+
+Possible sources for the SmartAgent:
+- The current KB (possibly several times with different filters)
+- Sync service (using connections defined in the current KB)
+- Google
+- Perplexity
+- MCP
+
+Out of scope
+- Other KBs
+- SQL
+- Snowflake (?)
+- Sitefinity (?)
+
+# Config spec
+
+```json
+{
+  "rephrase": { // optional
+    "ask_to": <filter_expression>, //optional
+    "prompt": <string>, // optional
+    "model": <model>, // optional
+  },
+  "smart_agent": {
+    "mode": <reactive | plan_execute>,
+    "extra_prompt": <string>, // optional
+    "models": { // optional
+      "context_validation": <model>, // optional
+      "planner": <model>, // optional
+      "executor": <model>, // optional
+    },
+    "sources": [<source list>]
+  },
+  "summarize": { // optional
+    "user_prompt": <string>, // optional
+    "system_prompt": <string>, // optional
+    "conversational": <boolean>,
+    "model": <model>, // optional
+    // and citations must be forced to chunk-level
+  }
+}
+```
+
+And sources can be:
+
+```json
+{
+  "type": "nucliadb",
+  "description": <string>,
+  "filter_expression": <filter_expression>, //optional
+}
+
+{
+  "type": "sync",
+  "description": <string>,
+  "connection": <connection_id>
+}
+
+{
+  "type": "google",
+  "description": <string>
+}
+
+{
+  "type": "perplexity",
+  "description": <string>
+}
+
+{
+  "type": "mcp",
+  "description": <string>,
+  <...the MCP driver params>
+}
+````

nucliadb_agentic_api-1.0.0.post156/VERSION

@@ -0,0 +1 @@
+1.0.0.post156

nucliadb_agentic_api-1.0.0.post156/alembic/README

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

nucliadb_agentic_api-1.0.0.post156/alembic/env.py

@@ -0,0 +1,99 @@
+import os
+from logging.config import fileConfig
+
+from hyperforge.database import metadata
+from sqlalchemy import engine_from_config, pool
+
+from alembic import context
+from nucliadb_agentic_api.db import (
+    agentic_configs,  # noqa: F401
+    sources,  # noqa: F401
+)
+from nucliadb_agentic_api.db.settings import DataManagerSettings
+
+# 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
+
+current_dir = os.path.dirname(os.path.abspath(__file__))
+migrations_dir = os.path.dirname(current_dir)
+
+config.set_main_option("script_location", migrations_dir)
+
+# Configure Alembic to use our DATABASE_URL and our table definitions...
+if os.environ.get("POSTGRESQL_DSN") or os.environ.get("postgresql_dsn"):
+    url = DataManagerSettings().postgresql_dsn.split("?")[0]  # type: ignore
+    config.set_main_option("sqlalchemy.url", url)
+
+
+target_metadata = 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,
+        version_table="nucliadb_agentic_api_alembic_version",
+        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,
+            version_table="nucliadb_agentic_api_alembic_version",
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

nucliadb_agentic_api-1.0.0.post156/alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

nucliadb_agentic_api-1.0.0.post156/alembic/versions/7f3b2f92a8c1_add_agentic_config_table.py

@@ -0,0 +1,56 @@
+"""Add agentic config table
+
+Revision ID: 7f3b2f92a8c1
+Revises: None
+Create Date: 2026-05-30 00:00:00.000000
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "7f3b2f92a8c1"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "agentic_config_table",
+        sa.Column("account", sa.String(), nullable=False),
+        sa.Column("kbid", sa.String(), nullable=False),
+        sa.Column("agentic_id", sa.String(), nullable=False),
+        sa.Column("created", sa.DateTime(), server_default=sa.func.now()),
+        sa.Column("modified", sa.DateTime(), nullable=True),
+        sa.Column("title", sa.String(), nullable=True),
+        sa.Column("config", postgresql.JSONB(astext_type=sa.Text()), nullable=False),
+        sa.PrimaryKeyConstraint("account", "kbid", "agentic_id"),
+    )
+    op.create_index(
+        op.f("ix_agentic_config_table_account"),
+        "agentic_config_table",
+        ["account"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("ix_agentic_config_table_kbid"),
+        "agentic_config_table",
+        ["kbid"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        op.f("ix_agentic_config_table_kbid"), table_name="agentic_config_table"
+    )
+    op.drop_index(
+        op.f("ix_agentic_config_table_account"), table_name="agentic_config_table"
+    )
+    op.drop_table("agentic_config_table")

nucliadb_agentic_api-1.0.0.post156/alembic/versions/b3c4d5e6f7a8_add_sources_table.py

@@ -0,0 +1,72 @@
+"""Add sources table
+
+Revision ID: b3c4d5e6f7a8
+Revises: 7f3b2f92a8c1
+Create Date: 2026-06-08 00:00:00.000000
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "b3c4d5e6f7a8"
+down_revision: Union[str, None] = "7f3b2f92a8c1"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "sources_table",
+        sa.Column("account", sa.String(), nullable=False),
+        sa.Column("kbid", sa.String(), nullable=False),
+        sa.Column("source_id", sa.String(), nullable=False),
+        sa.Column("agentic_config_id", sa.String(), nullable=True),
+        sa.Column("created", sa.DateTime(), server_default=sa.func.now()),
+        sa.Column("modified", sa.DateTime(), nullable=True),
+        sa.Column("description", sa.String(), nullable=True),
+        sa.Column("type", sa.String(), nullable=False),
+        sa.Column("config", postgresql.JSONB(astext_type=sa.Text()), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["account", "kbid", "agentic_config_id"],
+            [
+                "agentic_config_table.account",
+                "agentic_config_table.kbid",
+                "agentic_config_table.agentic_id",
+            ],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("account", "kbid", "source_id"),
+    )
+    op.create_index(
+        op.f("ix_sources_table_account"),
+        "sources_table",
+        ["account"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("ix_sources_table_kbid"),
+        "sources_table",
+        ["kbid"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("ix_sources_table_agentic_config_id"),
+        "sources_table",
+        ["agentic_config_id"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        op.f("ix_sources_table_agentic_config_id"), table_name="sources_table"
+    )
+    op.drop_index(op.f("ix_sources_table_kbid"), table_name="sources_table")
+    op.drop_index(op.f("ix_sources_table_account"), table_name="sources_table")
+    op.drop_table("sources_table")

nucliadb_agentic_api-1.0.0.post156/alembic.ini

@@ -0,0 +1,149 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+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
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be 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 <script_location>/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 "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# 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
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = postgresql://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 module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+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