Adding the rest

docs/60-perform-semantic-search/_category_.json

@@ -1,6 +1,6 @@
 {
   "label": "Perform Semantic Search on Your Data",
-  "position": 7,
+  "position": 6,
   "link": {
     "type": "generated-index",
     "description": "Retrieve semantically relevant documents to the user query using vector search."

docs/70-build-rag-app/1-concepts.mdx

@@ -1,7 +1,3 @@
 # 📘 Tools, libraries, and concepts
 
-Here is a quick overview of tools, libraries and concepts that you will come across in this section of the lab:
-
-## [RunnableWithMessageHistory](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html)
-
-Runnable that manages (reads, updates) chat message history for another Runnable. By default, it organizes chat history based on a session ID.
+TO-DO

docs/70-build-rag-app/2-build-rag-app.mdx

@@ -0,0 +1,50 @@
+# 👐 Build the RAG application
+
+Let's create a simple RAG application that takes in a user query, retrieves contextually relevant documents from MongoDB Atlas, and passes the query and retrieved context to the _Llama 3 8B Instruct_ model to generate an answer to the user question.
+
+Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 9: Build the RAG application** section in the notebook to build the RAG application.
+
+The answers for code blocks in this section are as follows:
+
+**CODE_BLOCK_20**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+vector_search(user_query)
+```
+</div>
+</details>
+
+**CODE_BLOCK_21**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+"\n\n".join([d.get("page_content", "") for d in context])
+```
+</div>
+</details>
+
+**CODE_BLOCK_22**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+response = fw_client.chat.completions.create(
+    model=model,
+    temperature=0,
+    messages=[
+        {
+            "role": "user",
+            "content": create_prompt(user_query),
+        }
+    ],
+)
+print(response.choices[0].message.content)
+```
+</div>
+</details>

docs/70-build-rag-app/3-stream-responses.mdx

@@ -0,0 +1,41 @@
+# 🦹 Stream responses from the RAG application
+
+By default, generation results are return once the generation is completed. Another option is to stream the results, which is useful for chat use cases where the user can incrementally see results as each token is generated.
+
+Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **🦹‍♀️ Return streaming responses** section in the notebook to stream the results from your RAG application.
+
+The answers for code blocks in this section are as follows:
+
+**CODE_BLOCK_23**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+fw_client.chat.completions.create(
+    model=model,
+    temperature=0,
+    stream=True,
+    messages=[
+        {
+            "role": "user",
+            "content": create_prompt(user_query),
+        }
+    ],
+)
+```
+</div>
+</details>
+
+**CODE_BLOCK_24**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+for chunk in response:
+    if chunk.choices[0].delta.content:
+        print(chunk.choices[0].delta.content, end="")
+```
+</div>
+</details>

docs/70-build-rag-app/_category_.json

@@ -1,6 +1,6 @@
 {
   "label": "Build the RAG Application",
-  "position": 8,
+  "position": 7,
   "link": {
     "type": "generated-index",
     "description": "Build the RAG application."

docs/80-add-memory/1-concepts.mdx

@@ -0,0 +1,3 @@
+# 📘 Tools, libraries, and concepts
+
+TO-DO

docs/80-add-memory/2-add-memory.mdx

@@ -0,0 +1,103 @@
+# 👐 Add memory to the RAG application
+
+In many Q&A applications we want to allow the user to have a back-and-forth conversation with the LLM, meaning the application needs some sort of "memory" of past questions and answers, and some logic for incorporating those into its current thinking. In this section, you will retrieve chat message history from MongoDB and incorporate it in your RAG application.
+
+Fill in any `<CODE_BLOCK_N>` placeholders and run the cells under the **Step 10: Add memory to the RAG application** section in the notebook to add memory to the RAG application.
+
+The answers for code blocks in this section are as follows:
+
+**CODE_BLOCK_25**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+history_collection.create_index("session_id")
+```
+</div>
+</details>
+
+**CODE_BLOCK_26**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+{
+    "session_id": session_id,
+    "role": role,
+    "content": content,
+    "timestamp": datetime.now(),
+}
+```
+</div>
+</details>
+
+**CODE_BLOCK_27**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+history_collection.insert_one(message)
+```
+</div>
+</details>
+
+**CODE_BLOCK_28**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+history_collection.find({"session_id": session_id}).sort("timestamp", 1)
+```
+</div>
+</details>
+
+**CODE_BLOCK_29**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+{"role": msg["role"], "content": msg["content"]} for msg in cursor
+```
+</div>
+</details>
+
+**CODE_BLOCK_30**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+message_history = retrieve_session_history(session_id)
+messages += message_history
+```
+</div>
+</details>
+
+**CODE_BLOCK_31**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+user_message = {"role": "user", "content": user_query}
+messages.append(user_message)
+```
+</div>
+</details>
+
+**CODE_BLOCK_32**
+
+<details>
+<summary>Answer</summary>
+<div>
+```python
+store_chat_message(session_id, "user", user_query)
+store_chat_message(session_id, "assistant", answer)
+```
+</div>
+</details>

docs/80-add-memory/_category_.json

@@ -0,0 +1,8 @@
+{
+  "label": "Add memory to the RAG application",
+  "position": 8,
+  "link": {
+    "type": "generated-index",
+    "description": "Retrieve chat message history from MongoDB and incorporate it into the RAG application."
+  }
+}

docs/summary.mdx

@@ -5,11 +5,11 @@ sidebar_position: 100
 # 🎯 Summary
 
 Congratulations! Following this lab, you have successfully:
-* learned what are AI agents
-* learned when to use AI agents
-* built a basic tool-calling agent
-* built a ReAct agent
-* built an agent with memory
+* learned what is Retrieval Augmented Generation a.k.a. RAG
+* learned when to use RAG
+* learned how to perform semantic search against data in MongoDB
+* built a RAG application
+* added memory to your RAG application
 
 Here are some resources that you might find helpful:
 * [MongoDB Developer Center](https://mongodb.com/developer/?utm_campaign=devrel&utm_source=workshop&utm_medium=cta&utm_content=ai_agents_workshop&utm_term=apoorva_joshi)