Google imagen integration

from langchain.messages import AIMessage, HumanMessage
from langchain_google_vertexai.vision_models import VertexAIImageGeneratorChat

# Create Image Generation model Object
generator = VertexAIImageGeneratorChat()

messages = [HumanMessage(content=["a cat at the beach"])]
response = generator.invoke(messages)

# To view the generated Image
generated_image = response.content[0]

import base64
import io

from PIL import Image

# Parse response object to get base64 string for image
img_base64 = generated_image["image_url"]["url"].split(",")[-1]

# Convert base64 string to Image
img = Image.open(io.BytesIO(base64.decodebytes(bytes(img_base64, "utf-8"))))

# view Image
img

from langchain.messages import AIMessage, HumanMessage
from langchain_google_vertexai.vision_models import (
    VertexAIImageEditorChat,
    VertexAIImageGeneratorChat,
)

# Create Image Generation model Object
generator = VertexAIImageGeneratorChat()

# Provide a text input for image
messages = [HumanMessage(content=["a cat at the beach"])]

# call the model to generate an image
response = generator.invoke(messages)

# read the image object from the response
generated_image = response.content[0]

# Create Image Editor model Object
editor = VertexAIImageEditorChat()

# Write prompt for editing and pass the "generated_image"
messages = [HumanMessage(content=[generated_image, "a dog at the beach "])]

# Call the model for editing Image
editor_response = editor.invoke(messages)

import base64
import io

from PIL import Image

# Parse response object to get base64 string for image
edited_img_base64 = editor_response.content[0]["image_url"]["url"].split(",")[-1]

# Convert base64 string to Image
edited_img = Image.open(
    io.BytesIO(base64.decodebytes(bytes(edited_img_base64, "utf-8")))
)

# view Image
edited_img

from langchain_google_vertexai import VertexAIImageCaptioning

# Initialize the Image Captioning Object
model = VertexAIImageCaptioning()

# use image generated in Image Generation Section
img_base64 = generated_image["image_url"]["url"]
response = model.invoke(img_base64)
print(f"Generated Caption : {response}")

# Convert base64 string to Image
img = Image.open(
    io.BytesIO(base64.decodebytes(bytes(img_base64.split(",")[-1], "utf-8")))
)

# display Image
img

Generated Cpation : a cat sitting on the beach looking at the camera

from langchain_google_vertexai import VertexAIVisualQnAChat

model = VertexAIVisualQnAChat()

question = "What animal is shown in the image?"
response = model.invoke(
    input=[
        HumanMessage(
            content=[
                {"type": "image_url", "image_url": {"url": img_base64}},
                question,
            ]
        )
    ]
)

print(f"question : {question}\nanswer : {response.content}")

# Convert base64 string to Image
img = Image.open(
    io.BytesIO(base64.decodebytes(bytes(img_base64.split(",")[-1], "utf-8")))
)

# display Image
img

question : What animal is shown in the image?
answer : cat