mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-01 03:16:23 +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
|
|
@ -4,36 +4,33 @@ Graph embeddings query service. Input is vector, output is list of
|
|||
entities. Pinecone implementation.
|
||||
"""
|
||||
|
||||
from pinecone import Pinecone, ServerlessSpec
|
||||
from pinecone.grpc import PineconeGRPC, GRPCClientConfig
|
||||
|
||||
import logging
|
||||
import uuid
|
||||
import os
|
||||
|
||||
from .... schema import GraphEmbeddingsRequest, GraphEmbeddingsResponse
|
||||
from pinecone import Pinecone, ServerlessSpec
|
||||
from pinecone.grpc import PineconeGRPC, GRPCClientConfig
|
||||
|
||||
from .... schema import GraphEmbeddingsResponse
|
||||
from .... schema import Error, Value
|
||||
from .... schema import graph_embeddings_request_queue
|
||||
from .... schema import graph_embeddings_response_queue
|
||||
from .... base import ConsumerProducer
|
||||
from .... base import GraphEmbeddingsQueryService
|
||||
|
||||
module = "ge-query"
|
||||
# Module logger
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
default_input_queue = graph_embeddings_request_queue
|
||||
default_output_queue = graph_embeddings_response_queue
|
||||
default_subscriber = module
|
||||
default_ident = "ge-query"
|
||||
default_api_key = os.getenv("PINECONE_API_KEY", "not-specified")
|
||||
|
||||
class Processor(ConsumerProducer):
|
||||
class Processor(GraphEmbeddingsQueryService):
|
||||
|
||||
def __init__(self, **params):
|
||||
|
||||
input_queue = params.get("input_queue", default_input_queue)
|
||||
output_queue = params.get("output_queue", default_output_queue)
|
||||
subscriber = params.get("subscriber", default_subscriber)
|
||||
|
||||
self.url = params.get("url", None)
|
||||
self.api_key = params.get("api_key", default_api_key)
|
||||
|
||||
if self.api_key is None or self.api_key == "not-specified":
|
||||
raise RuntimeError("Pinecone API key must be specified")
|
||||
|
||||
if self.url:
|
||||
|
||||
self.pinecone = PineconeGRPC(
|
||||
|
|
@ -47,12 +44,8 @@ class Processor(ConsumerProducer):
|
|||
|
||||
super(Processor, self).__init__(
|
||||
**params | {
|
||||
"input_queue": input_queue,
|
||||
"output_queue": output_queue,
|
||||
"subscriber": subscriber,
|
||||
"input_schema": GraphEmbeddingsRequest,
|
||||
"output_schema": GraphEmbeddingsResponse,
|
||||
"url": self.url,
|
||||
"api_key": self.api_key,
|
||||
}
|
||||
)
|
||||
|
||||
|
|
@ -62,26 +55,23 @@ class Processor(ConsumerProducer):
|
|||
else:
|
||||
return Value(value=ent, is_uri=False)
|
||||
|
||||
async def handle(self, msg):
|
||||
async def query_graph_embeddings(self, msg):
|
||||
|
||||
try:
|
||||
|
||||
v = msg.value()
|
||||
|
||||
# Sender-produced ID
|
||||
id = msg.properties()["id"]
|
||||
|
||||
print(f"Handling input {id}...", flush=True)
|
||||
# Handle zero limit case
|
||||
if msg.limit <= 0:
|
||||
return []
|
||||
|
||||
entity_set = set()
|
||||
entities = []
|
||||
|
||||
for vec in v.vectors:
|
||||
for vec in msg.vectors:
|
||||
|
||||
dim = len(vec)
|
||||
|
||||
index_name = (
|
||||
"t-" + v.user + "-" + str(dim)
|
||||
"t-" + msg.user + "-" + msg.collection + "-" + str(dim)
|
||||
)
|
||||
|
||||
index = self.pinecone.Index(index_name)
|
||||
|
|
@ -89,9 +79,8 @@ class Processor(ConsumerProducer):
|
|||
# Heuristic hack, get (2*limit), so that we have more chance
|
||||
# of getting (limit) entities
|
||||
results = index.query(
|
||||
namespace=v.collection,
|
||||
vector=vec,
|
||||
top_k=v.limit * 2,
|
||||
top_k=msg.limit * 2,
|
||||
include_values=False,
|
||||
include_metadata=True
|
||||
)
|
||||
|
|
@ -106,10 +95,10 @@ class Processor(ConsumerProducer):
|
|||
entities.append(ent)
|
||||
|
||||
# Keep adding entities until limit
|
||||
if len(entity_set) >= v.limit: break
|
||||
if len(entity_set) >= msg.limit: break
|
||||
|
||||
# Keep adding entities until limit
|
||||
if len(entity_set) >= v.limit: break
|
||||
if len(entity_set) >= msg.limit: break
|
||||
|
||||
ents2 = []
|
||||
|
||||
|
|
@ -118,37 +107,17 @@ class Processor(ConsumerProducer):
|
|||
|
||||
entities = ents2
|
||||
|
||||
print("Send response...", flush=True)
|
||||
r = GraphEmbeddingsResponse(entities=entities, error=None)
|
||||
await self.send(r, properties={"id": id})
|
||||
|
||||
print("Done.", flush=True)
|
||||
return entities
|
||||
|
||||
except Exception as e:
|
||||
|
||||
print(f"Exception: {e}")
|
||||
|
||||
print("Send error response...", flush=True)
|
||||
|
||||
r = GraphEmbeddingsResponse(
|
||||
error=Error(
|
||||
type = "llm-error",
|
||||
message = str(e),
|
||||
),
|
||||
entities=None,
|
||||
)
|
||||
|
||||
await self.send(r, properties={"id": id})
|
||||
|
||||
self.consumer.acknowledge(msg)
|
||||
logger.error(f"Exception querying graph embeddings: {e}", exc_info=True)
|
||||
raise e
|
||||
|
||||
@staticmethod
|
||||
def add_args(parser):
|
||||
|
||||
ConsumerProducer.add_args(
|
||||
parser, default_input_queue, default_subscriber,
|
||||
default_output_queue,
|
||||
)
|
||||
GraphEmbeddingsQueryService.add_args(parser)
|
||||
|
||||
parser.add_argument(
|
||||
'-a', '--api-key',
|
||||
|
|
@ -163,5 +132,5 @@ class Processor(ConsumerProducer):
|
|||
|
||||
def run():
|
||||
|
||||
Processor.launch(module, __doc__)
|
||||
Processor.launch(default_ident, __doc__)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue