trustgraph/trustgraph-flow/pyproject.toml

135 lines
5.7 KiB
TOML
Raw Normal View History

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "trustgraph-flow"
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 = [
2026-04-21 21:36:46 +01:00
"trustgraph-base>=2.4,<2.5",
"aiohttp",
"anthropic",
"scylla-driver",
"cohere",
"cryptography",
"faiss-cpu",
"falkordb",
"fastembed",
"ibis",
"jsonschema",
"langchain",
"langchain-community",
"langchain-core",
"langchain-text-splitters",
"mcp",
"minio",
"mistralai<2.0.0",
"neo4j",
"nltk",
"ollama",
"openai",
"pinecone[grpc]",
"prometheus-client",
"pulsar-client",
"pymilvus",
"pypdf",
"pyyaml",
"qdrant-client",
"rdflib",
"requests",
"strawberry-graphql",
"tabulate",
"tiktoken",
"urllib3",
]
classifiers = [
"Programming Language :: Python :: 3",
"Operating System :: OS Independent",
]
[project.urls]
Homepage = "https://github.com/trustgraph-ai/trustgraph"
[project.scripts]
agent-manager-react = "trustgraph.agent.react:run"
agent-orchestrator = "trustgraph.agent.orchestrator:run"
api-gateway = "trustgraph.gateway:run"
chunker-recursive = "trustgraph.chunking.recursive:run"
chunker-token = "trustgraph.chunking.token:run"
feat: pluggable bootstrap framework with ordered initialisers Replaces the previous pair of single-purpose bootstrap processors (config_bootstrap + pulsar_bootstrap) with a generic Bootstrapper that runs a configurable list of pluggable "initialisers" in a reconciliation loop. Design ------ See docs/tech-specs/bootstrap.md for the full spec. The bootstrapper is a single AsyncProcessor that: * Reads a list of initialiser specifications (class, name, flag, params) from either a direct `initialisers` parameter (processor-group embedding) or a YAML/JSON file (`-c`, CLI). * On each wake, runs a cheap service-gate (config-svc + flow-svc round-trips), then iterates the initialiser list, running each whose configured flag differs from the one stored in __system__/init-state/<name>. * Stores per-initialiser completion state in the reserved __system__ workspace; services never see these keys because of the _-prefix notification filter. * Adapts cadence: ~5s on gate failure, ~15s while converging, ~300s in steady state. * Isolates failures — one initialiser's exception does not block others in the same cycle; the failed one retries next wake. Initialiser contract -------------------- * Subclass trustgraph.bootstrap.base.Initialiser. * Implement async run(ctx, old_flag, new_flag). * Opt out of the service gate with class attr wait_for_services=False (only used by PulsarTopology — config-svc cannot come up until Pulsar namespaces exist). * ctx carries short-lived config and flow-svc clients plus a scoped logger. Core initialisers (trustgraph.bootstrap.initialisers.*) ------------------------------------------------------- * PulsarTopology — creates Pulsar tenant + namespaces (pre-gate, blocking HTTP offloaded to executor). * TemplateSeed — seeds __template__ from an external JSON file; re-run is upsert-missing by default, overwrite-all opt-in. * WorkspaceInit — populates a named workspace from either __template__ (with an explicit types list) or a seed file; raises cleanly if the template isn't seeded yet (retries on next cycle). * DefaultFlowStart — starts a specific flow in a workspace; no-ops if the flow is already running. Enterprise or third-party initialisers plug in via fully-qualified dotted class paths in the bootstrapper's configuration — no core code change required. pyproject.toml -------------- * Replaces config-bootstrap + pulsar-bootstrap entries with a single `bootstrap` script pointing at the new Processor.
2026-04-22 10:15:51 +01:00
bootstrap = "trustgraph.bootstrap.bootstrapper:run"
config-svc = "trustgraph.config.service:run"
Flow service lifecycle management (#822) feat: separate flow service from config service with explicit queue lifecycle management The flow service is now an independent service that owns the lifecycle of flow and blueprint queues. System services own their own queues. Consumers never create queues. Flow service separation: - New service at trustgraph-flow/trustgraph/flow/service/ - Uses async ConfigClient (RequestResponse pattern) to talk to config service - Config service stripped of all flow handling Queue lifecycle management: - PubSubBackend protocol gains create_queue, delete_queue, queue_exists, ensure_queue — all async - RabbitMQ: implements via pika with asyncio.to_thread internally - Pulsar: stubs for future admin REST API implementation - Consumer _connect() no longer creates queues (passive=True for named queues) - System services call ensure_queue on startup - Flow service creates queues on flow start, deletes on flow stop - Flow service ensures queues for pre-existing flows on startup Two-phase flow stop: - Phase 1: set flow status to "stopping", delete processor config entries - Phase 2: retry queue deletion, then delete flow record Config restructure: - active-flow config replaced with processor:{name} types - Each processor has its own config type, each flow variant is a key - Flow start/stop use batch put/delete — single config push per operation - FlowProcessor subscribes to its own type only Blueprint format: - Processor entries split into topics and parameters dicts - Flow interfaces use {"flow": "topic"} instead of bare strings - Specs (ConsumerSpec, ProducerSpec, etc.) read from definition["topics"] Tests updated
2026-04-16 17:19:39 +01:00
flow-svc = "trustgraph.flow.service:run"
doc-embeddings-query-milvus = "trustgraph.query.doc_embeddings.milvus:run"
doc-embeddings-query-pinecone = "trustgraph.query.doc_embeddings.pinecone:run"
doc-embeddings-query-qdrant = "trustgraph.query.doc_embeddings.qdrant:run"
doc-embeddings-write-milvus = "trustgraph.storage.doc_embeddings.milvus:run"
doc-embeddings-write-pinecone = "trustgraph.storage.doc_embeddings.pinecone:run"
doc-embeddings-write-qdrant = "trustgraph.storage.doc_embeddings.qdrant:run"
document-embeddings = "trustgraph.embeddings.document_embeddings:run"
document-rag = "trustgraph.retrieval.document_rag:run"
embeddings-fastembed = "trustgraph.embeddings.fastembed:run"
embeddings-ollama = "trustgraph.embeddings.ollama:run"
graph-embeddings-query-milvus = "trustgraph.query.graph_embeddings.milvus:run"
graph-embeddings-query-pinecone = "trustgraph.query.graph_embeddings.pinecone:run"
graph-embeddings-query-qdrant = "trustgraph.query.graph_embeddings.qdrant:run"
graph-embeddings-write-milvus = "trustgraph.storage.graph_embeddings.milvus:run"
graph-embeddings-write-pinecone = "trustgraph.storage.graph_embeddings.pinecone:run"
graph-embeddings-write-qdrant = "trustgraph.storage.graph_embeddings.qdrant:run"
graph-embeddings = "trustgraph.embeddings.graph_embeddings:run"
graph-rag = "trustgraph.retrieval.graph_rag:run"
kg-extract-agent = "trustgraph.extract.kg.agent:run"
kg-extract-definitions = "trustgraph.extract.kg.definitions:run"
kg-extract-rows = "trustgraph.extract.kg.rows:run"
kg-extract-relationships = "trustgraph.extract.kg.relationships:run"
kg-extract-topics = "trustgraph.extract.kg.topics:run"
kg-extract-ontology = "trustgraph.extract.kg.ontology:run"
kg-manager = "trustgraph.cores:run"
kg-store = "trustgraph.storage.knowledge:run"
librarian = "trustgraph.librarian:run"
mcp-tool = "trustgraph.agent.mcp_tool:run"
metering = "trustgraph.metering:run"
2025-09-04 13:39:47 +01:00
nlp-query = "trustgraph.retrieval.nlp_query:run"
rows-write-cassandra = "trustgraph.storage.rows.cassandra:run"
rows-query-cassandra = "trustgraph.query.rows.cassandra:run"
row-embeddings = "trustgraph.embeddings.row_embeddings:run"
row-embeddings-write-qdrant = "trustgraph.storage.row_embeddings.qdrant:run"
row-embeddings-query-qdrant = "trustgraph.query.row_embeddings.qdrant:run"
pdf-decoder = "trustgraph.decoding.pdf:run"
pdf-ocr-mistral = "trustgraph.decoding.mistral_ocr:run"
prompt-template = "trustgraph.prompt.template:run"
rev-gateway = "trustgraph.rev_gateway:run"
run-processing = "trustgraph.processing:run"
sparql-query = "trustgraph.query.sparql:run"
structured-query = "trustgraph.retrieval.structured_query:run"
structured-diag = "trustgraph.retrieval.structured_diag:run"
text-completion-azure = "trustgraph.model.text_completion.azure:run"
text-completion-azure-openai = "trustgraph.model.text_completion.azure_openai:run"
text-completion-claude = "trustgraph.model.text_completion.claude:run"
text-completion-cohere = "trustgraph.model.text_completion.cohere:run"
text-completion-llamafile = "trustgraph.model.text_completion.llamafile:run"
text-completion-lmstudio = "trustgraph.model.text_completion.lmstudio:run"
text-completion-mistral = "trustgraph.model.text_completion.mistral:run"
text-completion-ollama = "trustgraph.model.text_completion.ollama:run"
text-completion-openai = "trustgraph.model.text_completion.openai:run"
text-completion-tgi = "trustgraph.model.text_completion.tgi:run"
text-completion-vllm = "trustgraph.model.text_completion.vllm:run"
triples-query-cassandra = "trustgraph.query.triples.cassandra:run"
triples-query-falkordb = "trustgraph.query.triples.falkordb:run"
triples-query-memgraph = "trustgraph.query.triples.memgraph:run"
triples-query-neo4j = "trustgraph.query.triples.neo4j:run"
triples-write-cassandra = "trustgraph.storage.triples.cassandra:run"
triples-write-falkordb = "trustgraph.storage.triples.falkordb:run"
triples-write-memgraph = "trustgraph.storage.triples.memgraph:run"
triples-write-neo4j = "trustgraph.storage.triples.neo4j:run"
wikipedia-lookup = "trustgraph.external.wikipedia:run"
joke-service = "trustgraph.tool_service.joke:run"
[tool.setuptools.packages.find]
include = ["trustgraph*"]
[tool.setuptools.dynamic]
version = {attr = "trustgraph.flow_version.__version__"}