ƒeat(agents-api): Allow confidence control for embeddings search in s…

…ystem-type tools (#673)

<!-- ELLIPSIS_HIDDEN -->



> [!IMPORTANT]
> Adds confidence control to document search in `execute_system()` and
updates `README.md` with Julep vs. LangChain comparison.
> 
>   - **Behavior**:
> - Adds `confidence` parameter to `HybridDocSearchRequest` and
`VectorDocSearchRequest` in `execute_system()` for agent and user
document searches, defaulting to 0.7.
>   - **Documentation**:
> - Adds "Why Julep vs. LangChain?" section in `README.md` with
sub-sections on use cases, form factor, and summary.
> 
> <sup>This description was created by </sup>[<img alt="Ellipsis"
src="https://img.shields.io/badge/Ellipsis-blue?color=175173">](https://www.ellipsis.dev?ref=julep-ai%2Fjulep&utm_source=github&utm_medium=referral)<sup>
for 56a9559. It will automatically
update as commits are pushed.</sup>

<!-- ELLIPSIS_HIDDEN -->

---------

Co-authored-by: HamadaSalhab <[email protected]>

README.md

@@ -97,6 +97,10 @@ Exciting news! We're participating in DevFest.AI throughout October 2024! 🗓
 - [Local Quickstart](#local-quickstart)
 - [SDK Reference](#sdk-reference)
 - [API Reference](#api-reference)
+- [Why Julep vs. LangChain?](#why-julep-vs-langchain)
+  - [Different Use Cases](#different-use-cases)
+  - [Different Form Factor](#different-form-factor)
+  - [In Summary](#in-summary)
 
 </details>
 <!-- END doctoc generated TOC please keep comment here to allow auto update -->

agents-api/agents_api/activities/execute_system.py

@@ -107,6 +107,7 @@ async def execute_system(
                         search_params = HybridDocSearchRequest(
                             text=arguments.pop("text"),
                             vector=arguments.pop("vector"),
+                            confidence=arguments.pop("confidence", 0.7),
                             limit=arguments.get("limit", 10),
                         )
 
@@ -118,6 +119,7 @@ async def execute_system(
                     elif "vector" in arguments:
                         search_params = VectorDocSearchRequest(
                             vector=arguments.pop("vector"),
+                            confidence=arguments.pop("confidence", 0.7),
                             limit=arguments.get("limit", 10),
                         )