update code during demo

2_prompt_templates/1_prompt_template_basic.py

@@ -1,44 +1,47 @@
+# Prompt Template Docs:
+#   https://python.langchain.com/v0.2/docs/concepts/#prompt-templateshttps://python.langchain.com/v0.2/docs/concepts/#prompt-templates
+
 from langchain.prompts import ChatPromptTemplate
 from langchain_core.messages import HumanMessage
 
-# PART 1: Create a ChatPromptTemplate using a template string
-template = "Tell me a joke about {topic}."
-prompt_template = ChatPromptTemplate.from_template(template)
+# # PART 1: Create a ChatPromptTemplate using a template string
+# template = "Tell me a joke about {topic}."
+# prompt_template = ChatPromptTemplate.from_template(template)
 
-print("-----Prompt from Template-----")
-prompt = prompt_template.invoke({"topic": "cats"})
-print(prompt)
+# print("-----Prompt from Template-----")
+# prompt = prompt_template.invoke({"topic": "cats"})
+# print(prompt)
 
-# PART 2: Prompt with Multiple Placeholders
-template_multiple = """You are a helpful assistant.
-Human: Tell me a {adjective} story about a {animal}.
-Assistant:"""
-prompt_multiple = ChatPromptTemplate.from_template(template_multiple)
-prompt = prompt_multiple.invoke({"adjective": "funny", "animal": "panda"})
-print("\n----- Prompt with Multiple Placeholders -----\n")
-print(prompt)
+# # PART 2: Prompt with Multiple Placeholders
+# template_multiple = """You are a helpful assistant.
+# Human: Tell me a {adjective} story about a {animal}.
+# Assistant:"""
+# prompt_multiple = ChatPromptTemplate.from_template(template_multiple)
+# prompt = prompt_multiple.invoke({"adjective": "funny", "animal": "panda"})
+# print("\n----- Prompt with Multiple Placeholders -----\n")
+# print(prompt)
 
 
 # PART 3: Prompt with System and Human Messages (Using Tuples)
-messages = [
-    ("system", "You are a comedian who tells jokes about {topic}."),
-    ("human", "Tell me {joke_count} jokes."),
-]
-prompt_template = ChatPromptTemplate.from_messages(messages)
-prompt = prompt_template.invoke({"topic": "lawyers", "joke_count": 3})
-print("\n----- Prompt with System and Human Messages (Tuple) -----\n")
-print(prompt)
-
-# Extra Informoation about Part 3.
-# This does work:
-messages = [
-    ("system", "You are a comedian who tells jokes about {topic}."),
-    HumanMessage(content="Tell me 3 jokes."),
-]
-prompt_template = ChatPromptTemplate.from_messages(messages)
-prompt = prompt_template.invoke({"topic": "lawyers"})
-print("\n----- Prompt with System and Human Messages (Tuple) -----\n")
-print(prompt)
+# messages = [
+#     ("system", "You are a comedian who tells jokes about {topic}."),
+#     ("human", "Tell me {joke_count} jokes."),
+# ]
+# prompt_template = ChatPromptTemplate.from_messages(messages)
+# prompt = prompt_template.invoke({"topic": "lawyers", "joke_count": 3})
+# print("\n----- Prompt with System and Human Messages (Tuple) -----\n")
+# print(prompt)
+
+# # Extra Informoation about Part 3.
+# # This does work:
+# messages = [
+#     ("system", "You are a comedian who tells jokes about {topic}."),
+#     HumanMessage(content="Tell me 3 jokes."),
+# ]
+# prompt_template = ChatPromptTemplate.from_messages(messages)
+# prompt = prompt_template.invoke({"topic": "lawyers"})
+# print("\n----- Prompt with System and Human Messages (Tuple) -----\n")
+# print(prompt)
 
 
 # This does NOT work:

3_chains/1_chains_basics.py

@@ -19,6 +19,7 @@
 
 # Create the combined chain using LangChain Expression Language (LCEL)
 chain = prompt_template | model | StrOutputParser()
+# chain = prompt_template | model
 
 # Run the chain
 result = chain.invoke({"topic": "lawyers", "joke_count": 3})

3_chains/4_chains_parallel.py

@@ -1,7 +1,7 @@
 from dotenv import load_dotenv
 from langchain.prompts import ChatPromptTemplate
 from langchain.schema.output_parser import StrOutputParser
-from langchain.schema.runnable import RunnableBranch, RunnableLambda
+from langchain.schema.runnable import RunnableParallel, RunnableLambda
 from langchain_openai import ChatOpenAI
 
 # Load environment variables from .env
@@ -53,20 +53,21 @@ def combine_pros_cons(pros, cons):
 
 
 # Simplify branches with LCEL
-pros_branch = (
-    RunnableLambda(lambda x: analyze_pros(x["features"])) | model | StrOutputParser()
+pros_branch_chain = (
+    RunnableLambda(lambda x: analyze_pros(x)) | model | StrOutputParser()
 )
-cons_branch = (
-    RunnableLambda(lambda x: analyze_cons(x["features"])) | model | StrOutputParser()
+
+cons_branch_chain = (
+    RunnableLambda(lambda x: analyze_cons(x)) | model | StrOutputParser()
 )
 
 # Create the combined chain using LangChain Expression Language (LCEL)
 chain = (
     prompt_template
     | model
-    | RunnableLambda(lambda x: {"features": x})
-    | RunnableBranch(branches={"pros": pros_branch, "cons": cons_branch})
-    | RunnableLambda(lambda x: combine_pros_cons(x["pros"], x["cons"]))
+    | StrOutputParser()
+    | RunnableParallel(branches={"pros": pros_branch_chain, "cons": cons_branch_chain})
+    | RunnableLambda(lambda x: combine_pros_cons(x["branches"]["pros"], x["branches"]["cons"]))
 )
 
 # Run the chain

3_chains/5_chains_branching.py

@@ -1,7 +1,7 @@
 from dotenv import load_dotenv
 from langchain.prompts import ChatPromptTemplate
 from langchain.schema.output_parser import StrOutputParser
-from langchain.schema.runnable import RunnableableMap, RunnableBranch
+from langchain.schema.runnable import RunnableBranch
 from langchain_openai import ChatOpenAI
 
 # Load environment variables from .env
@@ -14,14 +14,16 @@
 positive_feedback_template = ChatPromptTemplate.from_messages(
     [
         ("system", "You are a helpful assistant."),
-        ("human", "Generate a thank you note for this positive feedback: {feedback}."),
+        ("human",
+         "Generate a thank you note for this positive feedback: {feedback}."),
     ]
 )
 
 negative_feedback_template = ChatPromptTemplate.from_messages(
     [
         ("system", "You are a helpful assistant."),
-        ("human", "Generate a response addressing this negative feedback: {feedback}."),
+        ("human",
+         "Generate a response addressing this negative feedback: {feedback}."),
     ]
 )
 
@@ -45,41 +47,46 @@
     ]
 )
 
-
-# Define the branch conditions based on feedback sentiment
-def is_positive(feedback):
-    return "good" in feedback.lower() or "excellent" in feedback.lower()
-
-
-def is_negative(feedback):
-    return "bad" in feedback.lower() or "poor" in feedback.lower()
-
-
-def is_neutral(feedback):
-    return "okay" in feedback.lower() or "neutral" in feedback.lower()
-
+# Define the feedback classification template
+classification_template = ChatPromptTemplate.from_messages(
+    [
+        ("system", "You are a helpful assistant."),
+        ("human",
+         "Classify the sentiment of this feedback as positive, negative, neutral, or escalate: {feedback}."),
+    ]
+)
 
 # Define the runnable branches for handling feedback
 branches = RunnableBranch(
-    (lambda x: is_positive(x), positive_feedback_template | model | StrOutputParser()),
-    (lambda x: is_negative(x), negative_feedback_template | model | StrOutputParser()),
-    (lambda x: is_neutral(x), neutral_feedback_template | model | StrOutputParser()),
-    escalate_feedback_template | model | StrOutputParser(),
+    (
+        lambda x: "positive" in x,
+        positive_feedback_template | model | StrOutputParser()  # Positive feedback chain
+    ),
+    (
+        lambda x: "negative" in x,
+        negative_feedback_template | model | StrOutputParser()  # Negative feedback chain
+    ),
+    (
+        lambda x: "neutral" in x,
+        neutral_feedback_template | model | StrOutputParser()  # Neutral feedback chain
+    ),
+    escalate_feedback_template | model | StrOutputParser()
 )
 
-# Create the combined chain using LangChain Expression Language (LCEL)
-chain = branches
+# Create the classification chain
+classification_chain = classification_template | model | StrOutputParser()
+
+# Combine classification and response generation into one chain
+chain = classification_chain | branches
 
 # Run the chain with an example review
 # Good review - "The product is excellent. I really enjoyed using it and found it very helpful."
 # Bad review - "The product is terrible. It broke after just one use and the quality is very poor."
 # Neutral review - "The product is okay. It works as expected but nothing exceptional."
 # Default - "I'm not sure about the product yet. Can you tell me more about its features and benefits?"
 
-review = (
-    "The product is terrible. It broke after just one use and the quality is very poor."
-)
-result = chain.invoke(review)
+review = "The product is terrible. It broke after just one use and the quality is very poor."
+result = chain.invoke({"feedback": review})
 
 # Output the result
 print(result)