mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 08:26:21 +02:00
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
This commit is contained in:
cybermaggedon
GitHub
parent
c85ba197be
commit
89be656990
509 changed files with 49632 additions and 5159 deletions
203
tests/unit/test_knowledge_graph/conftest.py
Normal file
203
tests/unit/test_knowledge_graph/conftest.py
Normal file
|
|
@ -0,0 +1,203 @@
|
|||
"""
|
||||
Shared fixtures for knowledge graph unit tests
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import Mock, AsyncMock
|
||||
|
||||
# Mock schema classes for testing
|
||||
class Value:
|
||||
def __init__(self, value, is_uri, type):
|
||||
self.value = value
|
||||
self.is_uri = is_uri
|
||||
self.type = type
|
||||
|
||||
class Triple:
|
||||
def __init__(self, s, p, o):
|
||||
self.s = s
|
||||
self.p = p
|
||||
self.o = o
|
||||
|
||||
class Metadata:
|
||||
def __init__(self, id, user, collection, metadata):
|
||||
self.id = id
|
||||
self.user = user
|
||||
self.collection = collection
|
||||
self.metadata = metadata
|
||||
|
||||
class Triples:
|
||||
def __init__(self, metadata, triples):
|
||||
self.metadata = metadata
|
||||
self.triples = triples
|
||||
|
||||
class Chunk:
|
||||
def __init__(self, metadata, chunk):
|
||||
self.metadata = metadata
|
||||
self.chunk = chunk
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_text():
|
||||
"""Sample text for entity extraction testing"""
|
||||
return "John Smith works for OpenAI in San Francisco. He is a software engineer who developed GPT models."
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_entities():
|
||||
"""Sample extracted entities for testing"""
|
||||
return [
|
||||
{"text": "John Smith", "type": "PERSON", "start": 0, "end": 10},
|
||||
{"text": "OpenAI", "type": "ORG", "start": 21, "end": 27},
|
||||
{"text": "San Francisco", "type": "GPE", "start": 31, "end": 44},
|
||||
{"text": "software engineer", "type": "TITLE", "start": 55, "end": 72},
|
||||
{"text": "GPT models", "type": "PRODUCT", "start": 87, "end": 97}
|
||||
]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_relationships():
|
||||
"""Sample extracted relationships for testing"""
|
||||
return [
|
||||
{"subject": "John Smith", "predicate": "works_for", "object": "OpenAI"},
|
||||
{"subject": "OpenAI", "predicate": "located_in", "object": "San Francisco"},
|
||||
{"subject": "John Smith", "predicate": "has_title", "object": "software engineer"},
|
||||
{"subject": "John Smith", "predicate": "developed", "object": "GPT models"}
|
||||
]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_value_uri():
|
||||
"""Sample URI Value object"""
|
||||
return Value(
|
||||
value="http://example.com/person/john-smith",
|
||||
is_uri=True,
|
||||
type=""
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_value_literal():
|
||||
"""Sample literal Value object"""
|
||||
return Value(
|
||||
value="John Smith",
|
||||
is_uri=False,
|
||||
type="string"
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_triple(sample_value_uri, sample_value_literal):
|
||||
"""Sample Triple object"""
|
||||
return Triple(
|
||||
s=sample_value_uri,
|
||||
p=Value(value="http://schema.org/name", is_uri=True, type=""),
|
||||
o=sample_value_literal
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_triples(sample_triple):
|
||||
"""Sample Triples batch object"""
|
||||
metadata = Metadata(
|
||||
id="test-doc-123",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
metadata=[]
|
||||
)
|
||||
|
||||
return Triples(
|
||||
metadata=metadata,
|
||||
triples=[sample_triple]
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_chunk():
|
||||
"""Sample text chunk for processing"""
|
||||
metadata = Metadata(
|
||||
id="test-chunk-456",
|
||||
user="test_user",
|
||||
collection="test_collection",
|
||||
metadata=[]
|
||||
)
|
||||
|
||||
return Chunk(
|
||||
metadata=metadata,
|
||||
chunk=b"Sample text chunk for knowledge graph extraction."
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_nlp_model():
|
||||
"""Mock NLP model for entity recognition"""
|
||||
mock = Mock()
|
||||
mock.process_text.return_value = [
|
||||
{"text": "John Smith", "label": "PERSON", "start": 0, "end": 10},
|
||||
{"text": "OpenAI", "label": "ORG", "start": 21, "end": 27}
|
||||
]
|
||||
return mock
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_entity_extractor():
|
||||
"""Mock entity extractor"""
|
||||
def extract_entities(text):
|
||||
if "John Smith" in text:
|
||||
return [
|
||||
{"text": "John Smith", "type": "PERSON", "confidence": 0.95},
|
||||
{"text": "OpenAI", "type": "ORG", "confidence": 0.92}
|
||||
]
|
||||
return []
|
||||
|
||||
return extract_entities
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_relationship_extractor():
|
||||
"""Mock relationship extractor"""
|
||||
def extract_relationships(entities, text):
|
||||
return [
|
||||
{"subject": "John Smith", "predicate": "works_for", "object": "OpenAI", "confidence": 0.88}
|
||||
]
|
||||
|
||||
return extract_relationships
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def uri_base():
|
||||
"""Base URI for testing"""
|
||||
return "http://trustgraph.ai/kg"
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def namespace_mappings():
|
||||
"""Namespace mappings for URI generation"""
|
||||
return {
|
||||
"person": "http://trustgraph.ai/kg/person/",
|
||||
"org": "http://trustgraph.ai/kg/org/",
|
||||
"place": "http://trustgraph.ai/kg/place/",
|
||||
"schema": "http://schema.org/",
|
||||
"rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
||||
}
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def entity_type_mappings():
|
||||
"""Entity type to namespace mappings"""
|
||||
return {
|
||||
"PERSON": "person",
|
||||
"ORG": "org",
|
||||
"GPE": "place",
|
||||
"LOCATION": "place"
|
||||
}
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def predicate_mappings():
|
||||
"""Predicate mappings for relationships"""
|
||||
return {
|
||||
"works_for": "http://schema.org/worksFor",
|
||||
"located_in": "http://schema.org/location",
|
||||
"has_title": "http://schema.org/jobTitle",
|
||||
"developed": "http://schema.org/creator"
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue