update with prompt techniques

docs/src/llm/README.md

@@ -7,7 +7,7 @@ The full librechat documentation is available [here](https://www.librechat.ai/do
 
 Let's discover how to use LibreChat to create efficient and effective conversations with AI for developers.
 
-## Prompts history
+## History
 Prompts history allows users to save and load prompts for their conversations and easily access them later. Reusing prompts can save time and effort, especially when working with multiple conversations and keep track of the context and details of a conversation.
 
 ## Favorites

docs/src/services/README.md

@@ -44,15 +44,12 @@ Beyond the core platform and APIs, Google offers several specialized AI products
 - **Google AI Platform Notebooks (integrated into Vertex AI):** Jupyter Notebook environments hosted on Google Cloud. (Previously a separate offering, often confused with Google Colab.)
 - **Dialogflow CX:** A conversational AI platform for building complex conversational experiences.
 
-##  Manage models (ML Flow)
-MLflow provides tools for managing experiments, tracking model versions, deploying models to various environments, and managing models in a central registry. It's designed to be platform-agnostic, meaning it can work with many different cloud providers and even on-premises infrastructure.
-
 ## Function calling (langchain4j)
 Function calling is a feature that allows you to call functions from other services. It is useful for working with functions, such as APIs, and for interacting with models that require function calls.
 
 To use function calling, you need to specify the function name and arguments in the prompt. 
 
-Ressouces Jean François James
+
 
 ## Structured Outputs (Json Mode) 
 Json mode is a feature that allows you to send structured data to the model. It is useful for working with structured data, such as JSON objects, and for interacting with models that require structured input.
@@ -72,6 +69,8 @@ Hugging Face is a platform for researchers and developers to share, explore, and
 - Creating/deploy/customize a model
 - Pre-trained model, use behind the APIs, also a ML part, training model generation for use
 
+##  Manage models (ML Flow)
+MLflow provides tools for managing experiments, tracking model versions, deploying models to various environments, and managing models in a central registry. It's designed to be platform-agnostic, meaning it can work with many different cloud providers and even on-premises infrastructure.
 
 ## 🧪 Exercises
 

docs/src/use/README.md

@@ -27,13 +27,22 @@ By using "act as," you are establishing a specific context for the language mode
 on a prompt about a futuristic world where robots have become sentient."
 ```
 
-### Chain of Thought
+### Framework : Chain of Thought
 
 ![Chain of Thought](../assets/images/cot.png)
 
 Introduced in Wei et al. (2022), chain-of-thought (CoT) prompting enables complex reasoning capabilities through intermediate reasoning steps. You can combine it with few-shot prompting to get better results on more complex tasks that require reasoning before responding.
 [Prompting Guide with CoT](https://www.promptingguide.ai/techniques/cot)
 
+### Framework : ReAct Prompting
+Yao et al., 2022 introduced a framework named ReAct where LLMs are used to generate both reasoning traces and task-specific actions in an interleaved manner.
+
+Generating reasoning traces allow the model to induce, track, and update action plans, and even handle exceptions. The action step allows to interface with and gather information from external sources such as knowledge bases or environments.
+
+The ReAct framework can allow LLMs to interact with external tools to retrieve additional information that leads to more reliable and factual responses.
+[Prompting Guide with CoT](https://www.promptingguide.ai/techniques/react.en)
+
+
 ### Summarize
 Summary is a prompt engineering technique that involves providing a summary of a given document or text. It can helps for summarizing changelogs, articles, or other technical documents.