trustgraph-base 2.7.0__tar.gz → 2.7.1__tar.gz

{trustgraph_base-2.7.0 → trustgraph_base-2.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: trustgraph-base
-Version: 2.7.0
+Version: 2.7.1
 Summary: TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.
 Author-email: "trustgraph.ai" <security@trustgraph.ai>
 Project-URL: Homepage, https://github.com/trustgraph-ai/trustgraph

{trustgraph_base-2.7.0 → trustgraph_base-2.7.1}/trustgraph/base/__init__.py

@@ -44,6 +44,8 @@ from . agent_client import AgentClientSpec
 from . structured_query_client import StructuredQueryClientSpec
 from . reranker_client import RerankerClientSpec
 from . reranker_service import RerankerService
+from . keyword_index_service import KeywordIndexService
+from . keyword_index_client import KeywordIndexClientSpec, KeywordIndexClient
 from . row_embeddings_query_client import RowEmbeddingsQueryClientSpec
 from . collection_config_handler import CollectionConfigHandler
 from . audit_publisher import AuditPublisher

trustgraph_base-2.7.1/trustgraph/base/keyword_index_client.py

@@ -0,0 +1,44 @@
+
+import logging
+
+from . request_response_spec import RequestResponse, RequestResponseSpec
+from .. schema import KeywordIndexRequest, KeywordIndexResponse
+
+# Module logger
+logger = logging.getLogger(__name__)
+
+class KeywordIndexClient(RequestResponse):
+    async def query(self, query, limit=20, collection="default", timeout=30):
+
+        resp = await self.request(
+            KeywordIndexRequest(
+                query = query,
+                limit = limit,
+                collection = collection
+            ),
+            timeout=timeout
+        )
+
+        logger.debug("Keyword index response: %s", resp)
+
+        if resp.error:
+            raise RuntimeError(resp.error.message)
+
+        # Return ChunkMatch objects with chunk_id and score
+        return resp.chunks
+
+class KeywordIndexClientSpec(RequestResponseSpec):
+    def __init__(
+            self, request_name, response_name,
+    ):
+        super(KeywordIndexClientSpec, self).__init__(
+            request_name = request_name,
+            request_schema = KeywordIndexRequest,
+            response_name = response_name,
+            response_schema = KeywordIndexResponse,
+            impl = KeywordIndexClient,
+            # Flow definitions predating the keyword index don't declare
+            # these topics; bind only where they exist so one stale
+            # definition can't wedge the processor.
+            optional = True,
+        )

trustgraph_base-2.7.1/trustgraph/base/keyword_index_service.py

@@ -0,0 +1,132 @@
+"""
+Keyword index service base class.  A single service owns both sides of the
+lexical index: it consumes Chunk messages off the ingestion stream (the last
+message in the pipeline that still carries chunk text) and answers keyword
+search requests over what it has indexed.  Unlike the vector stores, ingest
+and query are not split into two processors: the first backend (SQLite FTS5)
+is a single-file index that cannot be shared between containers, so one
+process must own it.  Backends with a server (Elasticsearch/OpenSearch) can
+still be split later behind the same schema.
+"""
+
+from __future__ import annotations
+
+from argparse import ArgumentParser
+
+import logging
+
+from .. schema import Chunk
+from .. schema import KeywordIndexRequest, KeywordIndexResponse
+from .. schema import Error
+from .. exceptions import TooManyRequests
+
+from . flow_processor import FlowProcessor
+from . consumer_spec import ConsumerSpec
+from . producer_spec import ProducerSpec
+
+# Module logger
+logger = logging.getLogger(__name__)
+
+default_ident = "kw-index"
+default_concurrency = 10
+
+class KeywordIndexService(FlowProcessor):
+
+    def __init__(self, **params):
+
+        id = params.get("id")
+        concurrency = params.get("concurrency", default_concurrency)
+
+        super(KeywordIndexService, self).__init__(
+            **params | { "id": id }
+        )
+
+        self.register_specification(
+            ConsumerSpec(
+                name = "input",
+                schema = Chunk,
+                handler = self.on_chunk,
+            )
+        )
+
+        self.register_specification(
+            ConsumerSpec(
+                name = "request",
+                schema = KeywordIndexRequest,
+                handler = self.on_request,
+                concurrency = concurrency,
+            )
+        )
+
+        self.register_specification(
+            ProducerSpec(
+                name = "response",
+                schema = KeywordIndexResponse,
+            )
+        )
+
+    async def on_chunk(self, msg, consumer, flow):
+
+        try:
+
+            request = msg.value()
+
+            # Workspace comes from the flow the message arrived on.
+            await self.index_chunk(flow.workspace, request)
+
+        except TooManyRequests as e:
+            raise e
+
+        except Exception as e:
+
+            logger.error(f"Exception in keyword index store: {e}", exc_info=True)
+            raise e
+
+    async def on_request(self, msg, consumer, flow):
+
+        try:
+
+            request = msg.value()
+
+            # Sender-produced ID
+            id = msg.properties()["id"]
+
+            logger.debug(f"Handling keyword index query request {id}...")
+
+            chunks = await self.query_keyword_index(
+                flow.workspace, request,
+            )
+
+            logger.debug("Sending keyword index query response...")
+            r = KeywordIndexResponse(chunks=chunks, error=None)
+            await flow("response").send(r, properties={"id": id})
+
+            logger.debug("Keyword index query request completed")
+
+        except Exception as e:
+
+            logger.error(f"Exception in keyword index query service: {e}", exc_info=True)
+
+            logger.info("Sending error response...")
+
+            r = KeywordIndexResponse(
+                error=Error(
+                    type = "keyword-index-query-error",
+                    message = str(e),
+                ),
+                chunks=[],
+            )
+
+            await flow("response").send(r, properties={"id": id})
+
+    @staticmethod
+    def add_args(parser: ArgumentParser) -> None:
+
+        FlowProcessor.add_args(parser)
+
+        parser.add_argument(
+            '-c', '--concurrency',
+            type=int,
+            default=default_concurrency,
+            help=f'Number of concurrent requests (default: {default_concurrency})'
+        )

{trustgraph_base-2.7.0 → trustgraph_base-2.7.1}/trustgraph/base/request_response_spec.py

@@ -109,16 +109,28 @@ class RequestResponse(Subscriber):
 class RequestResponseSpec(Spec):
     def __init__(
             self, request_name, request_schema, response_name,
-            response_schema, impl=RequestResponse
+            response_schema, impl=RequestResponse, optional=False
     ):
         self.request_name = request_name
         self.request_schema = request_schema
         self.response_name = response_name
         self.response_schema = response_schema
         self.impl = impl
+        self.optional = optional
 
     def add(self, flow: Any, processor: Any, definition: dict[str, Any]) -> None:
 
+        # An optional client binds only when the flow definition declares
+        # its topics. Older definitions predating the topics would otherwise
+        # KeyError here during Flow construction, which wedges the whole
+        # processor in a start-flow retry loop; skipping instead leaves
+        # flow(name) returning None for the caller to handle per-request.
+        topics = definition.get("topics", {})
+        if self.optional and (
+                self.request_name not in topics
+                or self.response_name not in topics):
+            return
+
         request_metrics = ProducerMetrics(
             processor = flow.id, flow = flow.name, name = self.request_name
         )

trustgraph_base-2.7.1/trustgraph/base_version.py

@@ -0,0 +1 @@
+__version__ = "2.7.1"

{trustgraph_base-2.7.0 → trustgraph_base-2.7.1}/trustgraph/schema/services/query.py

@@ -71,6 +71,27 @@ document_embeddings_response_queue = queue('document-embeddings', cls='response'
 
 ############################################################################
 
+# Keyword index query - lexical (BM25) search over chunk text, the sparse
+# counterpart to the doc embeddings query above. Matches share the ChunkMatch
+# shape so both retrieval paths key on chunk_id; score is "higher is better"
+# in both (BM25 rank scores are negated by the service to match).
+
+@dataclass
+class KeywordIndexRequest:
+    query: str = ""
+    limit: int = 0
+    collection: str = ""
+
+@dataclass
+class KeywordIndexResponse:
+    error: Error | None = None
+    chunks: list[ChunkMatch] = field(default_factory=list)
+
+keyword_index_request_queue = queue('keyword-index', cls='request')
+keyword_index_response_queue = queue('keyword-index', cls='response')
+
+############################################################################
+
 # Row embeddings query - for semantic/fuzzy matching on row index values
 
 @dataclass

{trustgraph_base-2.7.0 → trustgraph_base-2.7.1}/trustgraph_base.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: trustgraph-base
-Version: 2.7.0
+Version: 2.7.1
 Summary: TrustGraph provides a means to run a pipeline of flexible AI processing components in a flexible means to achieve a processing pipeline.
 Author-email: "trustgraph.ai" <security@trustgraph.ai>
 Project-URL: Homepage, https://github.com/trustgraph-ai/trustgraph

{trustgraph_base-2.7.0 → trustgraph_base-2.7.1}/trustgraph_base.egg-info/SOURCES.txt

@@ -47,6 +47,8 @@ trustgraph/base/graph_embeddings_store_service.py
 trustgraph/base/graph_rag_client.py
 trustgraph/base/iam_client.py
 trustgraph/base/kafka_backend.py
+trustgraph/base/keyword_index_client.py
+trustgraph/base/keyword_index_service.py
 trustgraph/base/librarian_client.py
 trustgraph/base/librarian_spec.py
 trustgraph/base/llm_service.py

trustgraph_base-2.7.0/trustgraph/base_version.py

@@ -1 +0,0 @@
-__version__ = "2.7.0"