Feature/configure flows (#345)

- Keeps processing in different flows separate so that data can go to different stores / collections etc.
- Potentially supports different processing flows
- Tidies the processing API with common base-classes for e.g. LLMs, and automatic configuration of 'clients' to use the right queue names in a flow

tests/test-graph-rag

@@ -3,11 +3,18 @@
 import pulsar
 from trustgraph.clients.graph_rag_client import GraphRagClient
 
-rag = GraphRagClient(pulsar_host="pulsar://localhost:6650")
+rag = GraphRagClient(
+    pulsar_host="pulsar://localhost:6650",
+    subscriber="test1",
+    input_queue = "non-persistent://tg/request/graph-rag:default",
+    output_queue = "non-persistent://tg/response/graph-rag:default",
+)
 
-query="""
-This knowledge graph describes the Space Shuttle disaster.
-Present 20 facts which are present in the knowledge graph."""
+#query="""
+#This knowledge graph describes the Space Shuttle disaster.
+#Present 20 facts which are present in the knowledge graph."""
+
+query = "How many cats does Mark have?"
 
 resp = rag.request(query)