adding image and chaning docs and readme: (#15)

Author: stefanfrench

README.md

@@ -13,6 +13,10 @@ This Blueprint demonstrates how to use open-source models and a simple LLM workf
 
 It is designed to showcase a simpler alternative to more complex and/or resource demanding alternatives, such as RAG systems that rely on vectorDBs and/or long-context models with large token windows.
 
+<img src="./images/structured-qa-diagram.png" width="1200" alt="structure-qa Diagram" />
+
+📘 To explore this project further and discover other Blueprints, visit the [**Blueprints Hub**](https://developer-hub.mozilla.ai/blueprints/query-structured-documents-using-a-lightweight-llm-workflow).
+
 
 ### 👉 📖 For more detailed guidance on using this project, please visit our [Docs here](https://mozilla-ai.github.io/structured-qa/).
 

docs/images/structured-qa-diagram.png

@@ -1,7 +1,7 @@
 # **Structured-QA Blueprint**
 
 <div style="text-align: center;">
-  <img src="images/document-to-podcast-diagram.png" alt="Project Logo" style="width: 100%; margin-bottom: 1px; margin-top: 1px;">
+  <img src="images/structured-qa-diagram.png" alt="Project Logo" style="width: 100%; margin-bottom: 1px; margin-top: 1px;">
 </div>
 
 Blueprints empower developers to easily integrate AI capabilities into their projects using open-source models and tools.

docs/index.md

@@ -9,17 +9,14 @@ This system has the following core stages:
    Prepare the input document by extracting the different sections that compose the structure of the document.
    Split the sections and save them to separate files.
 
-🔎 **2. Find Relevant Section**
-   Given a list of sections and the input question, use the LLM to identify the section that looks more relevant.
+🔎 **2. Find Relevant and Retrieve Section**
+   Given a list of sections and the input question, use the LLM to identify the section that looks more relevant. Load the individual section to be passed to the next step.
 
-📄 **3. Retrieve Section**
-    Load the individual section to be passed to the next step.
-
-📗 **4. Answer Question**
+📗 **3. Answer Question**
    Use the LLM to answer the question based on the information available in the retrieved section.
 
 
-In case the LLM can't find an answer to the question, the stages 2 to 4 run on a loop until the LLM finds the answer.
+In case the LLM can't find an answer to the question, the stages 2 to 3 run on a loop until the LLM finds the answer.
 
 ---