More API doc hacking

docs/apis/README.md

@@ -56,16 +56,17 @@ Cons:
     using a basic REST API, particular if you want to cover all of the error
     scenarios well
 
-## Further reading
+## See also
 
 - [TrustGraph websocket overview](websocket.md)
 - [TrustGraph Pulsar overview](pulsar.md)
 - API details
+  - [Text completion](api-text-completion.md)
+  - [Prompt completion](api-prompt.md)
   - [Graph RAG](api-graph-rag.md)
-  - [Document load](api-document-load.md)
   - [Agent](api-agent.md)
   - [Embeddings](api-embeddings.md)
-  - [Text completion](api-text-completion.md)
   - [Graph embeddings](api-graph-embeddings.md)
   - [Triples query](api-triples-query.md)
+  - [Document load](api-document-load.md)
 

docs/apis/api-text-completion.md

@@ -56,7 +56,6 @@ e.g.
 Request:
 
 ```
-
 {
     "id": "blrqotfefnmnh7de-1",
     "service": "text-completion",
@@ -67,11 +66,9 @@ Request:
 }
 ```
 
-Responses:
+Response:
 
 ```
-
-
 {
     "id": "blrqotfefnmnh7de-1",
     "response": {
@@ -83,7 +80,7 @@ Responses:
 
 ## Pulsar
 
-The Pulsar schema for the Agent API is defined in Python code here:
+The Pulsar schema for the Text Completion API is defined in Python code here:
 
 https://github.com/trustgraph-ai/trustgraph/blob/master/trustgraph-base/trustgraph/schema/models.py
 

docs/apis/pulsar.md

@@ -0,0 +1,3 @@
+
+Coming soon
+