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-llm

@@ -3,14 +3,17 @@
 import pulsar
 from trustgraph.clients.llm_client import LlmClient
 
-llm = LlmClient(pulsar_host="pulsar://localhost:6650")
+llm = LlmClient(
+    pulsar_host="pulsar://pulsar:6650",
+    input_queue="non-persistent://tg/request/text-completion:default",
+    output_queue="non-persistent://tg/response/text-completion:default",
+    subscriber="test1",
+)
 
 system = "You are a lovely assistant."
-prompt="Write a funny limerick about a llama"
+prompt="what is 2 + 2 == 5"
 
 resp = llm.request(system, prompt)
 
 print(resp)
 
-
-