> For the complete documentation index, see [llms.txt](https://pmse.gitbook.io/pmse-dhdk/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://pmse.gitbook.io/pmse-dhdk/1.-project-charter/1.7-resources.md).

# 1.7 Resources

## Human Resources

<table><thead><tr><th width="186">Role</th><th width="202">Name</th><th>Code</th><th>Max effort</th></tr></thead><tbody><tr><td>Project Manager</td><td>Lucrezia Pograri</td><td>PM001</td><td>12 hours/week</td></tr><tr><td>AI Engineer /<br>NLP Specialist</td><td>John Doe</td><td>SP001</td><td>20 hours/week</td></tr><tr><td>Software Developer (DevOps)</td><td>Jane Smith</td><td>SD001</td><td>20 hours/week</td></tr><tr><td>UX/UI Designer</td><td>Alice Johnson</td><td>UI001</td><td>20 hours/week</td></tr><tr><td>QA Engineer</td><td>Bob Lee</td><td>QA001</td><td>20 hours/week</td></tr><tr><td>Deployment Team</td><td><p>Lucrezia Pograri</p><p>John Doe </p><p>Jane Smith </p><p>Alice Johnson </p><p>Bob Lee</p></td><td>DT000</td><td>90 hours/week</td></tr></tbody></table>

Each resource works part-time for 4 hours per day, with a 5-day work week.

* **Project Manager**: Responsible for overall project coordination and management, including overseeing timelines, resources, and deliverables.\
  Since the Project Manager is not always present, we can estimate that they work a reduced portion of the week. Let's assume the Project Manager works 3 days per week.
* **Software Developers:** Responsible for backend and frontend development, including AI integration and platform integration. Responsible for creating the user guides, technical documentation, and API documentation.
  * **AI Engineer** specialised in NLP tasks: Responsible for the design and implementation of the RAG AI-powered chatbot system.
  * **DevOps Engineer**: Manages deployment, hosting, and infrastructure scalability. Ideally, they have expertise in cloud DevOps environments.
* **UX/UI Designer**: Designing and prototyping user interface.
* **Quality Assurance (QA) Engineer**: Responsible for testing the system, including performance, scalability, and security testing.&#x20;
* **Customer Support:** For post-deployment user assistance and issue resolution.

***

## Technical Resources

* **Python:** A programming language particularly suited for software development in machine learning contexts.
* **Mistral LLM**: Provides embeddings for vector search and generates retrieval-augmented responses.
* **FAISS**: Efficiently indexes and retrieves chunks of text.
* **Streamlit**: Creates a web-based interface for interaction.
* **Pandas**: Manages and processes the dataset.
* **dotenv**: Loads API keys and configuration from environment variables.
* **LangChain**: Powers the conversational and retrieval logic.

## **Infrastructures**

* **Development Environment:** Cloud-based virtual machines or local systems for development and deployment.
* CRM systems and API tools for integration, for deploying a hosting environment for the web application (e.g., RESTful API).
* Persistent storage for the FAISS vector store and dataset.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://pmse.gitbook.io/pmse-dhdk/1.-project-charter/1.7-resources.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.