picachain 0.1.35

Build quick LLM pipelines for image specific tasks.

⚡️ Build quick LLM pipelines for all your image specific tasks

Picachain is a framework for building complex non language pipelines for your LLM application. Build pipelines for your images, charts and graphs, parse, extract and generate using opensource models with ease, thanks to support for huggingface and diffusion libraries.

🌉 Things you can build with Picachain

• Image Search Engines: Build quick search engines for your images using ChromaDB and Pinecone for vector storage and retrieval.
• Image Generation: Generate images with ease, thanks to support of Stable Diffusion, SDXL and SDXLturbo.
• Chart Parsing: Parse chart/graph from images and extract meaningful data and build a question-answering system on top of this using an LLM.

📌 Install Picachain

pip install picachain

🥇 Example Usage

Build a quick image search engine

Use ChromaDB or Pinecone for storage with CLIP embeddings. Check out a demo

from PIL import Image
import matplotlib.pyplot as plt

# import from picachain
from picachain.chains.image.search import ImageSearchChain
from picachain.datastore import ChromaStore, PineconeStore
from picachain.embedding import ClipEmbedding
from picachain.retriever import ImageRetriever

img = Image.open("image.png") # query image
images = [...] # list of images

# initiate embedding, datastore and retriever
embedding = ClipEmbedding()
datastore = ChromaStore("test-collection")
retriever = ImageRetriever(datastore, embedding, images)
img_chain = ImageSearchChain.from_image(retriever, embedding, img)
result = img_chain.similar_images(top_k=3)

for img, score in result: # [(img, score), (img, score)]
    plt.imshow(img)
    plt.show()

Build Chart Conversation Chain

from dotenv import load_dotenv
from picachain.chains.unstructured.charts import ChartConversationChain
from picachain.models.openai.openai import OpenAI_Model
load_dotenv()

chart_conv_chain = ChartConversationChain(
    chart="/home/home/dev/picachain/data/chart1.png", llm=OpenAI_Model()
)
response = chart_conv_chain.run(query="What do I eat?")
print(response)

💡 Contributing

As an open-source project, we are open to all kinds of contribution, be it through code, documentation, issues, bugs, or even feature suggestions.

Feel free to check out Contribution guide for more details.

🔧 Dependencies

We use poetry as the package manager. Make sure to refer to pyproject.toml for more details on dependencies.

cd picachain
pip install poetry
poetry install