trustgraph/trustgraph-cli/trustgraph/cli/init_trustgraph.py
cybermaggedon 89be656990
Release/v1.2 (#457)
* Bump setup.py versions for 1.1

* PoC MCP server (#419)

* Very initial MCP server PoC for TrustGraph

* Put service on port 8000

* Add MCP container and packages to buildout

* Update docs for API/CLI changes in 1.0 (#421)

* Update some API basics for the 0.23/1.0 API change

* Add MCP container push (#425)

* Add command args to the MCP server (#426)

* Host and port parameters

* Added websocket arg

* More docs

* MCP client support (#427)

- MCP client service
- Tool request/response schema
- API gateway support for mcp-tool
- Message translation for tool request & response
- Make mcp-tool using configuration service for information
  about where the MCP services are.

* Feature/react call mcp (#428)

Key Features

  - MCP Tool Integration: Added core MCP tool support with ToolClientSpec and ToolClient classes
  - API Enhancement: New mcp_tool method for flow-specific tool invocation
  - CLI Tooling: New tg-invoke-mcp-tool command for testing MCP integration
  - React Agent Enhancement: Fixed and improved multi-tool invocation capabilities
  - Tool Management: Enhanced CLI for tool configuration and management

Changes

  - Added MCP tool invocation to API with flow-specific integration
  - Implemented ToolClientSpec and ToolClient for tool call handling
  - Updated agent-manager-react to invoke MCP tools with configurable types
  - Enhanced CLI with new commands and improved help text
  - Added comprehensive documentation for new CLI commands
  - Improved tool configuration management

Testing

  - Added tg-invoke-mcp-tool CLI command for isolated MCP integration testing
  - Enhanced agent capability to invoke multiple tools simultaneously

* Test suite executed from CI pipeline (#433)

* Test strategy & test cases

* Unit tests

* Integration tests

* Extending test coverage (#434)

* Contract tests

* Testing embeedings

* Agent unit tests

* Knowledge pipeline tests

* Turn on contract tests

* Increase storage test coverage (#435)

* Fixing storage and adding tests

* PR pipeline only runs quick tests

* Empty configuration is returned as empty list, previously was not in response (#436)

* Update config util to take files as well as command-line text (#437)

* Updated CLI invocation and config model for tools and mcp (#438)

* Updated CLI invocation and config model for tools and mcp

* CLI anomalies

* Tweaked the MCP tool implementation for new model

* Update agent implementation to match the new model

* Fix agent tools, now all tested

* Fixed integration tests

* Fix MCP delete tool params

* Update Python deps to 1.2

* Update to enable knowledge extraction using the agent framework (#439)

* Implement KG extraction agent (kg-extract-agent)

* Using ReAct framework (agent-manager-react)
 
* ReAct manager had an issue when emitting JSON, which conflicts which ReAct manager's own JSON messages, so refactored ReAct manager to use traditional ReAct messages, non-JSON structure.
 
* Minor refactor to take the prompt template client out of prompt-template so it can be more readily used by other modules. kg-extract-agent uses this framework.

* Migrate from setup.py to pyproject.toml (#440)

* Converted setup.py to pyproject.toml

* Modern package infrastructure as recommended by py docs

* Install missing build deps (#441)

* Install missing build deps (#442)

* Implement logging strategy (#444)

* Logging strategy and convert all prints() to logging invocations

* Fix/startup failure (#445)

* Fix loggin startup problems

* Fix logging startup problems (#446)

* Fix logging startup problems (#447)

* Fixed Mistral OCR to use current API (#448)

* Fixed Mistral OCR to use current API

* Added PDF decoder tests

* Fix Mistral OCR ident to be standard pdf-decoder (#450)

* Fix Mistral OCR ident to be standard pdf-decoder

* Correct test

* Schema structure refactor (#451)

* Write schema refactor spec

* Implemented schema refactor spec

* Structure data mvp (#452)

* Structured data tech spec

* Architecture principles

* New schemas

* Updated schemas and specs

* Object extractor

* Add .coveragerc

* New tests

* Cassandra object storage

* Trying to object extraction working, issues exist

* Validate librarian collection (#453)

* Fix token chunker, broken API invocation (#454)

* Fix token chunker, broken API invocation (#455)

* Knowledge load utility CLI (#456)

* Knowledge loader

* More tests
2025-08-18 20:56:09 +01:00

239 lines
No EOL
6 KiB
Python

"""
Initialises Pulsar with Trustgraph tenant / namespaces & policy.
"""
import requests
import time
import argparse
import json
from trustgraph.clients.config_client import ConfigClient
default_pulsar_admin_url = "http://pulsar:8080"
default_pulsar_host = "pulsar://pulsar:6650"
subscriber = "tg-init-pulsar"
def get_clusters(url):
print("Get clusters...", flush=True)
resp = requests.get(f"{url}/admin/v2/clusters")
if resp.status_code != 200: raise RuntimeError("Could not fetch clusters")
return resp.json()
def ensure_tenant(url, tenant, clusters):
resp = requests.get(f"{url}/admin/v2/tenants/{tenant}")
if resp.status_code == 200:
print(f"Tenant {tenant} already exists.", flush=True)
return
resp = requests.put(
f"{url}/admin/v2/tenants/{tenant}",
json={
"adminRoles": [],
"allowedClusters": clusters,
}
)
if resp.status_code != 204:
print(resp.text, flush=True)
raise RuntimeError("Tenant creation failed.")
print(f"Tenant {tenant} created.", flush=True)
def ensure_namespace(url, tenant, namespace, config):
resp = requests.get(f"{url}/admin/v2/namespaces/{tenant}/{namespace}")
if resp.status_code == 200:
print(f"Namespace {tenant}/{namespace} already exists.", flush=True)
return
resp = requests.put(
f"{url}/admin/v2/namespaces/{tenant}/{namespace}",
json=config,
)
if resp.status_code != 204:
print(resp.status_code, flush=True)
print(resp.text, flush=True)
raise RuntimeError(f"Namespace {tenant}/{namespace} creation failed.")
print(f"Namespace {tenant}/{namespace} created.", flush=True)
def ensure_config(config, pulsar_host, pulsar_api_key):
cli = ConfigClient(
subscriber=subscriber,
pulsar_host=pulsar_host,
pulsar_api_key=pulsar_api_key,
)
while True:
try:
print("Get current config...", flush=True)
current, version = cli.config(timeout=5)
except Exception as e:
print("Exception:", e, flush=True)
time.sleep(2)
print("Retrying...", flush=True)
continue
print("Current config version is", version, flush=True)
if version != 0:
print("Already updated, not updating config. Done.", flush=True)
return
print("Config is version 0, updating...", flush=True)
batch = []
for type in config:
for key in config[type]:
print(f"Adding {type}/{key} to update.", flush=True)
batch.append({
"type": type,
"key": key,
"value": json.dumps(config[type][key]),
})
try:
cli.put(batch, timeout=10)
print("Update succeeded.", flush=True)
break
except Exception as e:
print("Exception:", e, flush=True)
time.sleep(2)
print("Retrying...", flush=True)
continue
def init(
pulsar_admin_url, pulsar_host, pulsar_api_key, tenant,
config, config_file,
):
clusters = get_clusters(pulsar_admin_url)
ensure_tenant(pulsar_admin_url, tenant, clusters)
ensure_namespace(pulsar_admin_url, tenant, "flow", {})
ensure_namespace(pulsar_admin_url, tenant, "request", {})
ensure_namespace(pulsar_admin_url, tenant, "response", {
"retention_policies": {
"retentionSizeInMB": -1,
"retentionTimeInMinutes": 3,
"subscriptionExpirationTimeMinutes": 30,
}
})
ensure_namespace(pulsar_admin_url, tenant, "config", {
"retention_policies": {
"retentionSizeInMB": 10,
"retentionTimeInMinutes": -1,
"subscriptionExpirationTimeMinutes": 5,
}
})
if config is not None:
try:
print("Decoding config...", flush=True)
dec = json.loads(config)
print("Decoded.", flush=True)
except Exception as e:
print("Exception:", e, flush=True)
raise e
ensure_config(dec, pulsar_host, pulsar_api_key)
elif config_file is not None:
try:
print("Decoding config...", flush=True)
dec = json.load(open(config_file))
print("Decoded.", flush=True)
except Exception as e:
print("Exception:", e, flush=True)
raise e
ensure_config(dec, pulsar_host, pulsar_api_key)
else:
print("No config to update.", flush=True)
def main():
parser = argparse.ArgumentParser(
prog='tg-init-trustgraph',
description=__doc__,
)
parser.add_argument(
'-p', '--pulsar-admin-url',
default=default_pulsar_admin_url,
help=f'Pulsar admin URL (default: {default_pulsar_admin_url})',
)
parser.add_argument(
'--pulsar-host',
default=default_pulsar_host,
help=f'Pulsar host (default: {default_pulsar_host})',
)
parser.add_argument(
'--pulsar-api-key',
help=f'Pulsar API key',
)
parser.add_argument(
'-c', '--config',
help=f'Initial configuration to load',
)
parser.add_argument(
'-C', '--config-file',
help=f'Initial configuration to load from file',
)
parser.add_argument(
'-t', '--tenant',
default="tg",
help=f'Tenant (default: tg)',
)
args = parser.parse_args()
while True:
try:
print(flush=True)
print(
f"Initialising with Pulsar {args.pulsar_admin_url}...",
flush=True
)
init(**vars(args))
print("Initialisation complete.", flush=True)
break
except Exception as e:
print("Exception:", e, flush=True)
print("Sleeping...", flush=True)
time.sleep(2)
print("Will retry...", flush=True)
if __name__ == "__main__":
main()