mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-09 07:12:37 +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
35
trustgraph-ocr/pyproject.toml
Normal file
35
trustgraph-ocr/pyproject.toml
Normal file
|
|
@ -0,0 +1,35 @@
|
|||
[build-system]
|
||||
requires = ["setuptools>=61.0", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "trustgraph-ocr"
|
||||
dynamic = ["version"]
|
||||
authors = [{name = "trustgraph.ai", email = "security@trustgraph.ai"}]
|
||||
description = "TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline."
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.8"
|
||||
dependencies = [
|
||||
"trustgraph-base>=1.2,<1.3",
|
||||
"pulsar-client",
|
||||
"prometheus-client",
|
||||
"boto3",
|
||||
"pdf2image",
|
||||
"pytesseract",
|
||||
]
|
||||
classifiers = [
|
||||
"Programming Language :: Python :: 3",
|
||||
"Operating System :: OS Independent",
|
||||
]
|
||||
|
||||
[project.urls]
|
||||
Homepage = "https://github.com/trustgraph-ai/trustgraph"
|
||||
|
||||
[project.scripts]
|
||||
pdf-ocr = "trustgraph.decoding.ocr:run"
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
include = ["trustgraph*"]
|
||||
|
||||
[tool.setuptools.dynamic]
|
||||
version = {attr = "trustgraph.ocr_version.__version__"}
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
from trustgraph.decoding.ocr import run
|
||||
|
||||
run()
|
||||
|
||||
|
|
@ -1,47 +0,0 @@
|
|||
import setuptools
|
||||
import os
|
||||
import importlib
|
||||
|
||||
with open("README.md", "r") as fh:
|
||||
long_description = fh.read()
|
||||
|
||||
# Load a version number module
|
||||
spec = importlib.util.spec_from_file_location(
|
||||
'version', 'trustgraph/ocr_version.py'
|
||||
)
|
||||
version_module = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(version_module)
|
||||
|
||||
version = version_module.__version__
|
||||
|
||||
setuptools.setup(
|
||||
name="trustgraph-ocr",
|
||||
version=version,
|
||||
author="trustgraph.ai",
|
||||
author_email="security@trustgraph.ai",
|
||||
description="TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.",
|
||||
long_description=long_description,
|
||||
long_description_content_type="text/markdown",
|
||||
url="https://github.com/trustgraph-ai/trustgraph",
|
||||
packages=setuptools.find_namespace_packages(
|
||||
where='./',
|
||||
),
|
||||
classifiers=[
|
||||
"Programming Language :: Python :: 3",
|
||||
"License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
|
||||
"Operating System :: OS Independent",
|
||||
],
|
||||
python_requires='>=3.8',
|
||||
download_url = "https://github.com/trustgraph-ai/trustgraph/archive/refs/tags/v" + version + ".tar.gz",
|
||||
install_requires=[
|
||||
"trustgraph-base>=1.0,<1.1",
|
||||
"pulsar-client",
|
||||
"prometheus-client",
|
||||
"boto3",
|
||||
"pdf2image",
|
||||
"pytesseract",
|
||||
],
|
||||
scripts=[
|
||||
"scripts/pdf-ocr",
|
||||
]
|
||||
)
|
||||
|
|
@ -6,12 +6,16 @@ PDF document as text as separate output objects.
|
|||
|
||||
import tempfile
|
||||
import base64
|
||||
import logging
|
||||
import pytesseract
|
||||
from pdf2image import convert_from_bytes
|
||||
|
||||
from ... schema import Document, TextDocument, Metadata
|
||||
from ... base import FlowProcessor, ConsumerSpec, ProducerSpec
|
||||
|
||||
# Module logger
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
default_ident = "pdf-decoder"
|
||||
|
||||
class Processor(FlowProcessor):
|
||||
|
|
@ -41,15 +45,15 @@ class Processor(FlowProcessor):
|
|||
)
|
||||
)
|
||||
|
||||
print("PDF OCR inited")
|
||||
logger.info("PDF OCR processor initialized")
|
||||
|
||||
async def on_message(self, msg, consumer, flow):
|
||||
|
||||
print("PDF message received", flush=True)
|
||||
logger.info("PDF message received")
|
||||
|
||||
v = msg.value()
|
||||
|
||||
print(f"Decoding {v.metadata.id}...", flush=True)
|
||||
logger.info(f"Decoding {v.metadata.id}...")
|
||||
|
||||
blob = base64.b64decode(v.data)
|
||||
|
||||
|
|
@ -60,7 +64,7 @@ class Processor(FlowProcessor):
|
|||
try:
|
||||
text = pytesseract.image_to_string(page, lang='eng')
|
||||
except Exception as e:
|
||||
print(f"Page did not OCR: {e}")
|
||||
logger.warning(f"Page did not OCR: {e}")
|
||||
continue
|
||||
|
||||
r = TextDocument(
|
||||
|
|
@ -70,7 +74,7 @@ class Processor(FlowProcessor):
|
|||
|
||||
await flow("output").send(r)
|
||||
|
||||
print("Done.", flush=True)
|
||||
logger.info("PDF decoding complete")
|
||||
|
||||
@staticmethod
|
||||
def add_args(parser):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue