diff --git a/chapter3.md b/chapter3.md
index 8b13789..1c1055d 100644
--- a/chapter3.md
+++ b/chapter3.md
@@ -1 +1,24 @@
+## Chapter 3: Prompt Engineering
+Prompt engineering is a very important concept in using LangChain. Designing the right prompts can help you get more accurate and useful answers from your AI model.
 
+```
+from langchain import PromptTemplate
+
+
+template = """
+You are a helpful assistant that translates {input_language} to {output_language}.
+
+Translate the following text:
+{text}
+
+Translation:
+"""
+
+prompt = PromptTemplate(
+    input_variables=["input_language", "output_language", "text"],
+    template=template
+)
+
+
+print(prompt.format(input_language="English", output_language="French", text="Hello, how are you?"))
+```
\ No newline at end of file
diff --git a/chapter4.md b/chapter4.md
new file mode 100644
index 0000000..9a8ea2e
--- /dev/null
+++ b/chapter4.md
@@ -0,0 +1,29 @@
+## Chapter 4: Building the Chain
+Chains are one of the core concepts of LangChain: multiple components can be chained together to perform more complex tasks.
+
+```
+from langchain.chains import SimpleSequentialChain
+from langchain.llms import OpenAI
+from langchain.prompts import PromptTemplate
+
+llm = OpenAI(temperature=0.7)
+
+first_prompt = PromptTemplate(
+    input_variables=["product"],
+    template="What is a good name for a company that makes {product}?",
+)
+chain_one = LLMChain(llm=llm, prompt=first_prompt)
+
+second_prompt = PromptTemplate(
+    input_variables=["company_name"],
+    template="Write a catchphrase for the following company: {company_name}",
+)
+chain_two = LLMChain(llm=llm, prompt=second_prompt)
+
+
+overall_chain = SimpleSequentialChain(chains=[chain_one, chain_two], verbose=True)
+
+
+print(overall_chain.run("eco-friendly water bottles"))
+
+```
\ No newline at end of file
diff --git a/chapter5.md b/chapter5.md
new file mode 100644
index 0000000..cf149a5
--- /dev/null
+++ b/chapter5.md
@@ -0,0 +1,23 @@
+## Chapter 5: Utilizing memory
+The memory component helps preserve the context of the conversation, making for a more natural dialogue.
+
+```
+from langchain.memory import ConversationBufferMemory
+from langchain.llms import OpenAI
+from langchain.chains import ConversationChain
+
+
+memory = ConversationBufferMemory()
+
+
+conversation = ConversationChain(
+    llm=OpenAI(temperature=0),
+    memory=memory,
+    verbose=True
+)
+
+
+print(conversation.predict(input="Hi, my name is Alice"))
+print(conversation.predict(input="What's my name?"))
+print(conversation.predict(input="What have we talked about so far?"))
+```
\ No newline at end of file
diff --git a/chapter6.md b/chapter6.md
new file mode 100644
index 0000000..d205498
--- /dev/null
+++ b/chapter6.md
@@ -0,0 +1,29 @@
+## Chapter 6: Document Retrieval and Question Answering
+You can use LangChain to build a system that searches through large amounts of documents for information and answers questions.
+
+```
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.llms import OpenAI
+from langchain.chains import RetrievalQA
+
+
+with open('your_document.txt', 'r') as file:
+    raw_text = file.read()
+
+
+text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+texts = text_splitter.split_text(raw_text)
+
+
+embeddings = OpenAIEmbeddings()
+docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{"source": str(i)} for i in range(len(texts))])
+
+
+qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever())
+
+
+query = "What is the main topic of this document?"
+print(qa.run(query))
+```
\ No newline at end of file
diff --git a/chapter7.md b/chapter7.md
new file mode 100644
index 0000000..e69de29
diff --git a/chapter8.md b/chapter8.md
new file mode 100644
index 0000000..216a7c5
--- /dev/null
+++ b/chapter8.md
@@ -0,0 +1 @@
+chapter4.md
\ No newline at end of file
diff --git a/chapter9.md b/chapter9.md
new file mode 100644
index 0000000..e69de29