%pip install langchain-google-genai

import getpassimport os if "GOOGLE_API_KEY" not in os.environ:    os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter your Google AI API key: ")

from langchain_google_genai import ChatGoogleGenerativeAI # Initialize modelllm = ChatGoogleGenerativeAI(    model="gemini-2.0-flash",    temperature=0,    max_tokens=None,    timeout=None,    max_retries=2,) # Simple invocationmessages = [    ("system", "You are a helpful assistant that translates English to French."),    ("human", "I love programming."),]response = llm.invoke(messages)print(response.content)  # Output: J'adore la programmation.

from langchain_google_genai import ChatGoogleGenerativeAIfrom langchain_core.prompts import ChatPromptTemplate # Initialize modelllm = ChatGoogleGenerativeAI(    model="gemini-2.0-flash",    temperature=0,) prompt = ChatPromptTemplate.from_messages([    ("system", "You are a helpful assistant that translates {input_language} to {output_language}."),    ("human", "{input}"),]) chain = prompt | llmresult = chain.invoke({    "input_language": "English",    "output_language": "German",    "input": "I love programming.",})print(result.content)  # Output: Ich liebe Programmieren.

from langchain_google_genai import ChatGoogleGenerativeAIfrom langchain_core.messages import HumanMessageimport base64 # Initialize modelllm = ChatGoogleGenerativeAI(model="gemini-2.0-flash") # Using an image URLmessage_url = HumanMessage(    content=[        {"type": "text", "text": "Describe this image."},        {"type": "image_url", "image_url": "https://picsum.photos/seed/picsum/200/300"},    ])result_url = llm.invoke([message_url])print(result_url.content) # Using a local imagelocal_image_path = "../assets/react.png"with open(local_image_path, "rb") as image_file:    encoded_image = base64.b64encode(image_file.read()).decode('utf-8') message_local = HumanMessage(    content=[        {"type": "text", "text": "Describe this image."},        {"type": "image_url", "image_url": f"data:image/png;base64,{encoded_image}"}    ])result_local = llm.invoke([message_local])print(result_local.content)

from langchain_google_genai import ChatGoogleGenerativeAIfrom langchain_core.messages import HumanMessageimport base64 # Initialize modelllm = ChatGoogleGenerativeAI(model="gemini-2.0-flash") audio_file_path = "../path/to/your/audio/file.mp3"audio_mime_type = "audio/mpeg" with open(audio_file_path, "rb") as audio_file:    encoded_audio = base64.b64encode(audio_file.read()).decode('utf-8') message = HumanMessage(    content=[        {"type": "text", "text": "Transcribe this audio."},        {"type": "media", "data": encoded_audio, "mime_type": audio_mime_type}    ])response = llm.invoke([message])print(response.content)

from langchain_google_genai import ChatGoogleGenerativeAIfrom langchain_core.messages import HumanMessageimport base64 # Initialize modelllm = ChatGoogleGenerativeAI(model="gemini-2.0-flash") video_file_path = "../path/to/your/video/file.mp4"video_mime_type = "video/mp4" with open(video_file_path, "rb") as video_file:    encoded_video = base64.b64encode(video_file.read()).decode('utf-8') message = HumanMessage(    content=[        {"type": "text", "text": "Describe what's happening in this video."},        {"type": "media", "data": encoded_video, "mime_type": video_mime_type}    ])response = llm.invoke([message])print(response.content)

from langchain_google_genai import ChatGoogleGenerativeAIimport base64from IPython.display import Image, display # Initialize model for image generationllm = ChatGoogleGenerativeAI(model="models/gemini-2.0-flash-exp-image-generation") message = {    "role": "user",    "content": "Generate an image of a cat wearing a hat.",} response = llm.invoke(    [message],    generation_config=dict(response_modalities=["TEXT", "IMAGE"]),) # Display the generated imageimage_base64 = response.content[0].get("image_url").get("url").split(",")[-1]image_data = base64.b64decode(image_base64)display(Image(data=image_data, width=300))

from langchain_google_genai import ChatGoogleGenerativeAIfrom langchain_core.tools import toolfrom langchain_core.messages import ToolMessage # Define a tool@tool(description="Get the current weather in a given location")def get_weather(location: str) -> str:    return "It's sunny." # Initialize model and bind the toolllm = ChatGoogleGenerativeAI(model="gemini-2.0-flash")llm_with_tools = llm.bind_tools([get_weather]) # Invoke with a query that should trigger the toolquery = "What's the weather in San Francisco?"ai_msg = llm_with_tools.invoke(query) # Access tool calls in the responseprint(ai_msg.tool_calls) # Pass tool results back to the modeltool_message = ToolMessage(    content=get_weather(*ai_msg.tool_calls[0]['args']),     tool_call_id=ai_msg.tool_calls[0]['id'])final_response = llm_with_tools.invoke([ai_msg, tool_message])print(final_response.content)

from langchain_google_genai import ChatGoogleGenerativeAIfrom google.ai.generativelanguage_v1beta.types import Tool as GenAITool # Initialize modelllm = ChatGoogleGenerativeAI(model="gemini-2.0-flash") # Google Searchsearch_resp = llm.invoke(    "When is the next total solar eclipse in US?",    tools=[GenAITool(google_search={})],)print(search_resp.content) # Code Executioncode_resp = llm.invoke(    "What is 2*2, use python",    tools=[GenAITool(code_execution={})],) for c in code_resp.content:    if isinstance(c, dict):        if c["type"] == 'code_execution_result':            print(f"Code execution result: {c['code_execution_result']}")        elif c["type"] == 'executable_code':            print(f"Executable code: {c['executable_code']}")    else:        print(c)

from langchain_core.pydantic_v1 import BaseModel, Fieldfrom langchain_google_genai import ChatGoogleGenerativeAI # Define the desired structureclass Person(BaseModel):    '''Information about a person.'''    name: str = Field(..., description="The person's name")    height_m: float = Field(..., description="The person's height in meters") # Initialize the modelllm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)structured_llm = llm.with_structured_output(Person) # Invoke the model with a query asking for structured informationresult = structured_llm.invoke("Who was the 16th president of the USA, and how tall was he in meters?")print(result)  # Output: name='Abraham Lincoln' height_m=1.93

from langchain_google_genai import ChatGoogleGenerativeAI # Initialize modelllm = ChatGoogleGenerativeAI(model="gemini-2.0-flash") result = llm.invoke("Explain the concept of prompt engineering in one sentence.") print(result.content)print("\nUsage Metadata:")print(result.usage_metadata)

from langchain_google_genai import GoogleGenerativeAIEmbeddings embeddings = GoogleGenerativeAIEmbeddings(model="models/gemini-embedding-exp-03-07") # Embed a single queryvector = embeddings.embed_query("hello, world!") # Embed multiple documentsvectors = embeddings.embed_documents([    "Today is Monday",    "Today is Tuesday",    "Today is April Fools day",])

from langchain_google_genai import GoogleGenerativeAIEmbeddingsfrom langchain_core.vectorstores import InMemoryVectorStore # Initialize embeddingsembeddings = GoogleGenerativeAIEmbeddings(model="models/gemini-embedding-exp-03-07") text = "LangChain is the framework for building context-aware reasoning applications" # Create vector store and retrievervectorstore = InMemoryVectorStore.from_texts([text], embedding=embeddings)retriever = vectorstore.as_retriever() # Retrieve similar documentsretrieved_documents = retriever.invoke("What is LangChain?")print(retrieved_documents[0].page_content)

%pip install scikit-learn

from langchain_google_genai import GoogleGenerativeAIEmbeddingsfrom sklearn.metrics.pairwise import cosine_similarity # Different task types for different use casesquery_embeddings = GoogleGenerativeAIEmbeddings(    model="models/gemini-embedding-exp-03-07",     task_type="RETRIEVAL_QUERY"  # For queries)doc_embeddings = GoogleGenerativeAIEmbeddings(    model="models/gemini-embedding-exp-03-07",     task_type="RETRIEVAL_DOCUMENT"  # For documents) # Compare similarityq_embed = query_embeddings.embed_query("What is the capital of France?")d_embed = doc_embeddings.embed_documents(["The capital of France is Paris.", "Philipp likes to eat pizza."]) for i, d in enumerate(d_embed):    similarity = cosine_similarity([q_embed], [d])[0][0]    print(f"Document {i+1} similarity: {similarity}")