Updated readme w/ Philosophy

Author: Kate Yanchenko

README.md

@@ -1,16 +1,25 @@
+
 # Lamoom
 
-## Introduction
+## Our Philosophy
+
+Lamoom, derived from "Lambda on Mechanisms," refers to computation within a system that iteratively guides the LLM to perform correctly. Inspired by Amazon’s culture, as Jeff Bezos said, "Good intentions don't work, mechanisms do," we focus on building mechanisms for LLMs rather than relying on their good intentions
+
+![Lamoom Mechanisms](docs/media/lamoom_mechanisms.gif)
 
+
+## Introduction
 Lamoom is a dynamic, all-in-one library designed for managing and optimizing prompts and making tests based on the ideal answer for large language models (LLMs) in production and R&D. It facilitates dynamic data integration, latency and cost metrics visibility, and efficient load distribution across multiple AI models.
 
+[![Lamoom Introduction Video](https://img.youtube.com/vi/1opO_5kRf98/0.jpg)](https://www.youtube.com/watch?v=1opO_5kRf98 "Lamoom Introduction Video")
+
 ## Features
 
 - **CI/CD testing**: Generates tests based on the context and ideal answer (usually written by the human).
 - **Dynamic Prompt Development**: Avoid budget exceptions with dynamic data.
 - **Multi-Model Support**: Seamlessly integrate with various LLMs like OpenAI, Anthropic, and more.
 - **Real-Time Insights**: Monitor interactions, request/response metrics in production.
-- **Prompt Testing and Evolution**: Quickly test and iterate on prompts using historical data.
+- **Prompt Testing and Evaluation**: Quickly test and iterate on prompts using historical data.
 - **Smart Prompt Caching**: Efficiently cache prompts for 5 minutes to reduce latency while keeping them updated.
 - **Asynchronous Logging**: Record interactions without blocking the main execution flow.
 
@@ -20,7 +29,7 @@ Lamoom is a dynamic, all-in-one library designed for managing and optimizing pro
 Lamoom implements an efficient prompt caching system with a 5-minute TTL (Time-To-Live):
 - **Automatic Updates**: When you call a prompt, Lamoom checks if a newer version exists on the server.
 - **Cache Invalidation**: Prompts are automatically refreshed after 5 minutes to ensure up-to-date content.
-- **Local Fallback**: If the server is unavailable, Lamoom falls back to the locally defined prompt.
+- **Local Fallback**: If the LamoomService is unavailable, Lamoom library falls back to the locally defined prompt.
 - **Version Control**: Track prompt versions between local and server instances.
 
 ![Lamoom Call Flow](docs/sequence_diagrams/pngs/lamoom_call.png)

docs/sequence_diagrams/add_ideal_answer_to_log.uml

@@ -1,24 +1,9 @@
 @startuml
 
   title Lamoom Feedback Flow: Adding ideal answers to existing responses
-
-  note over Client,LamoomService: Process of providing feedback on previous responses
-
-    Client->>Lamoom: add_ideal_answer(response_id, ideal_answer)
-    activate Lamoom
-
-    Lamoom->>LamoomService: update_response_ideal_answer(api_token, log_id, ideal_answer)
-    activate LamoomService
-
-    LamoomService->>LamoomService: Prepare feedback data
-
-    LamoomService->>LamoomService: PUT /lib/logs
-    note right of LamoomService: Server updates existing log with:\n- Ideal answer for comparison\n- Used for quality assessment\n- Creating training data\n- Generating automated tests
-
+  note over Lamoom,LamoomService: Process of providing feedback on previous responses
+    Lamoom->>Lamoom: add_ideal_answer(response_id, ideal_answer)
+    Lamoom->>LamoomService:  update_response_ideal_answer(api_token, log_id, ideal_answer)
+    note right of LamoomService: PUT /lib/logs: Server updates existing log with:\n- Ideal answer for comparison\n- Used for quality assessment\n- Creating training data\n- Generating automated tests
     LamoomService-->>Lamoom: Return feedback submission result
-    deactivate LamoomService
-
-    Lamoom-->>Client: Return feedback submission result
-    deactivate Lamoom
-
-  @enduml
+  @enduml

docs/sequence_diagrams/pngs/lamoom_add_ideal_answer.png

@@ -5,20 +5,13 @@
 
   note over Lamoom,LamoomService: Process of recording prompt execution logs
 
-    Lamoom->>Lamoom: call(prompt_id, context, model)
-    Lamoom->>LamoomService: Fetches prompt
-    Lamoom->>LLM: calls LLM, gets response
+    Lamoom->>Lamoom: call(prompt_id, context, model) - Fetches prompt, calls LLM, gets response
     note right of SaveWorker: Async worker for saving\ninteractions to avoid blocking
 
     Lamoom->>SaveWorker: add_task(api_token, prompt_data, context, result, test_data)
-    
+
     SaveWorker->>LamoomService: save_user_interaction(api_token, prompt_data, context, response)
-    
-    LamoomService->>LamoomService: POST /lib/logs
-    note right of LamoomService: Server records interaction for:\n- Analytics\n- Debugging\n- Performance tracking\n- Cost monitoring
-    
-    LamoomService-->>SaveWorker: Return result of logging operation
-    
+    note right of LamoomService: POST /lib/logs: Server records interaction for:\n- Analytics\n- Debugging\n- Performance tracking\n- Cost monitoring
     Lamoom-->>Lamoom: Return AIResponse (without waiting for log completion)
 
   @enduml

docs/sequence_diagrams/pngs/lamoom_call.png

@@ -1,17 +1,13 @@
 @startuml
 
-    Note over Lamoom,LibCache: Prompt Caching Flow (TTL: 5 minutes)
     Note over Lamoom,LLM: Process of lamoom.call(prompt_id, context, model)
 
-      Lamoom->>Lamoom: call(prompt_id, context, model)
       Lamoom->>LibCache: get_prompt(prompt_id, version)
-
-
-      alt Prompt is in cache or !API_SERVICE or RECEIVE_PROMPT_FROM_SERVER disabled
+      alt Prompt is in cache or RECEIVE_PROMPT_FROM_SERVER disabled
           Lamoom-->>LibCache: Return cached prompt data
       end
       alt Cache miss or expired or new version of prompt is in the code
-          LamoomService->>LamoomService: POST /lib/prompts (with currently active prompt data)
+          Lamoom->>LamoomService: POST /lib/prompts (with currently active prompt data)
 
           Note right of LamoomService: Server checks if local prompt\nis the latest published version
 

docs/sequence_diagrams/pngs/lamoom_save_user_interactions.png

@@ -4,34 +4,20 @@
 
   note over Lamoom,LamoomService: Process of creating tests for CI/CD validation
 
-    alt Direct test creation via create_test method
-      Client->>Lamoom: create_test(prompt_id, test_context, ideal_answer)
-      
-      Lamoom->>LamoomService: POST /lib/tests?createTest
+    alt Test creation via create_test method
+      Lamoom->>LamoomService: create_test(prompt_id, test_context, ideal_answer)
       note right of LamoomService: Server creates test with:\n- Prompt ID\n- Test context\n- Ideal answer
-      
+
       LamoomService-->>Lamoom: Return create test result
-      
-      Lamoom-->>Client: Return test creation result
     end
-    
-    alt Test creation during normal prompt call with test_data
-      Client->>Lamoom: call(prompt_id, context, model, test_data={ideal_answer})
 
-      Lamoom->>Lamoom: Fetches prompt, calls LLM, gets response
+    alt Test creation during normal prompt call with test_data
+      Lamoom->>Lamoom: call(prompt_id, context, model, test_data={ideal_answer}),  Fetches prompt, calls LLM, gets response
 
       Lamoom->>SaveWorker: add_task(api_token, prompt_data, context, result, test_data)
-      SaveWorker->>LamoomService: create_test_with_ideal_answer(api_token, prompt_data, context, test_data)
-
-      note right of LamoomService: If ideal_answer exists in test_data
-
-      LamoomService->>LamoomService: POST /lib/tests
-      note right of LamoomService: Server creates CI/CD test with:\n- Context\n- Prompt\n- Ideal answer\n- Behavior name
-
-      LamoomService-->>SaveWorker: Return (logs success message)
-
-      SaveWorker-->>Lamoom: (Async) Task complete
-      Lamoom-->>Client: Return AIResponse (without waiting for test creation)
+      SaveWorker->>LamoomService: create_test_with_ideal_answer
+      note right of LamoomService:  Server creates CI/CD test with:\n- Context\n- Prompt\n- Ideal answer
+      Lamoom-->>Lamoom: Return AIResponse (without waiting for test creation)
     end
 
-  @enduml
+  @enduml