@semiont/inference 0.2.32-build.69 → 0.2.32-build.71
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -16,6 +16,12 @@ This package provides the **core AI primitives** for the Semiont platform:
|
|
|
16
16
|
|
|
17
17
|
For **application-specific AI logic** (entity extraction, resource generation, motivation prompts/parsers), see [@semiont/make-meaning](../make-meaning/).
|
|
18
18
|
|
|
19
|
+
## Architecture Context
|
|
20
|
+
|
|
21
|
+
**Infrastructure Ownership**: In production applications, inference client instances are **created and managed by [@semiont/make-meaning](../make-meaning/)'s `startMakeMeaning()` function**, which serves as the single orchestration point for all infrastructure components (EventStore, GraphDB, RepStore, InferenceClient, JobQueue, Workers).
|
|
22
|
+
|
|
23
|
+
The API shown below can be used directly for **testing, CLI tools, or standalone scripts**. For backend integration, access the inference client through the `makeMeaning` context object.
|
|
24
|
+
|
|
19
25
|
## Philosophy
|
|
20
26
|
|
|
21
27
|
This package is named `inference` rather than `ai-inference` to align with Semiont's core tenet: humans and AI agents have equal opportunity to work behind similar interfaces. The abstraction remains open for future human-agent parity.
|
package/package.json
CHANGED