base on A realtime serving engine for Data-Intensive Generative AI Applications <a name="readme-top"></a> # Indexify  [](https://discord.gg/VXkY7zVmTD) ## Create and Deploy Durable, Data-Intensive Agentic Workflows *Indexify simplifies building and serving durable, multi-stage workflows as inter-connected Python functions and automagically deploys them as APIs.* A **workflow** encodes data ingestion and transformation stages that can be implemented using Python functions. Each of these functions is a logical compute unit that can be retried upon failure or assigned to specific hardware. <br /> <div align="center"> <img src="https://raw.githubusercontent.com/tensorlakeai/indexify/main/docs/images/PDF_Extraction_Demo-VEED.gif" alt="PDF Extraction Demo" style="width: 75%; height: auto;" loading="lazy" /> </div> <br /> *To give you a taste of the project, in the above video - Indexify running PDF Extraction on a cluster of 3 machines. </br> top left - A GPU accelerated machine running document layout and OCR model on a PDF,</br> bottom left - chunking texts, embedding image and text using CLIP and a text embedding model. </br> top right - A function writing image and text embeddings to ChromaDB. </br> All three functions of the workflow are running in parallel and coordinated by the Indexify server.* > [!NOTE] > Indexify is the Open-Source core compute engine that powers Tensorlake's Serverless Workflow Engine for processing unstructured data. ### 💡 Use Cases **Indexify** is a versatile data processing framework for all kinds of use cases, including: * [Scraping and Summarizing Websites](examples/website_audio_summary/) * [Extracting and Indexing PDF Documents](examples/pdf_document_extraction/) * [Transcribing and Summarizing Audio Files](examples/video_summarization/) * [Object Detection and Description](examples/object_detection/) * [Knowledge Graph RAG and Question Answering](examples/knowledge_graph/) ### ⭐ Key Features * **Dynamic Routing:** Route data to different specialized models based on conditional branching logic. * **Local Inference:** Execute LLMs directly within workflow functions using LLamaCPP, vLLM, or Hugging Face Transformers. * **Distributed Processing:** Run functions in parallel across machines so that results across functions can be combined as they complete. * **Workflow Versioning:** Version compute graphs to update previously processed data to reflect the latest functions and models. * **Resource Allocation:** Span workflows across GPU and CPU instances so that functions can be assigned to their optimal hardware. * **Request Optimization:** Maximize GPU utilization by automatically queuing and batching invocations in parallel. ## ⚙️ Installation Install Indexify's SDK and CLI into your development environment: ```bash pip install indexify ``` ## 📚 A Minimal Example Define a workflow by implementing its data transformation as composable Python functions. Functions decorated with `@indexify_function()`. These functions form the edges of a `Graph`, which is the representation of a compute graph. <br></br> Functions serve as discrete units within a Graph, defining the boundaries for retry attempts and resource allocation. They separate computationally heavy tasks like LLM inference from lightweight ones like database writes. <br></br> The example below is a pipeline that calculates the sum of squares for the first consecutive whole numbers. ```python from pydantic import BaseModel from indexify import indexify_function, indexify_router, Graph from typing import List, Union class Document(BaseModel): pages: List[str] # Parse a pdf and extract text @indexify_function() def process_document(file: File) -> Document: # Process a PDF and extract pages class TextChunk(BaseModel): chunk: str page_number: int # Chunk the pages for embedding and retreival @indexify_function() def chunk_document(document: Document) -> List[TextChunk]: # Split the pages # Embed a single chunk. # Note: (Automatic Map) Indexify automatically parallelize functions when they consume an element # from functions that produces a List @indexify_functions() def embed_and_write(chunk: TextChunk) -> ChunkEmbedding: # run an embedding model on the chunk # write_to_db # Constructs a compute graph connecting the three functions defined above into a workflow that generates # runs them as a pipeline graph = Graph(name="document_ingestion_pipeline", start_node=process_document, description="...") graph.add_edge(process_document, chunk_document) graph.add_edge(chunk_document, embed_and_write) ``` [Read the Docs](https://docs.tensorlake.ai/quick-start) to learn more about how to test, deploy and create API endpoints for Workflows. ## 📖 Next Steps * [Architecture of Indexify](https://docs.getindexify.ai/architecture) * [Packaging Dependencies of Functions](https://docs.getindexify.ai/packaging-dependencies) * [Programming Model](https://docs.getindexify.ai/key-concepts#programming-model) * [Deploying Compute Graph Endpoints using Docker Compose](https://docs.getindexify.ai/operations/deployment#docker-compose) * [Deploying Compute Graph Endpoints using Kubernetes](https://docs.getindexify.ai/operations/deployment#kubernetes) ### 🗺️ Roadmap #### ⏳ Scheduler * **Function Batching:** Process multiple functions in a single batch to improve efficiency. * **Data Localized Execution:** Boost performance by prioritizing execution on machines where intermediate outputs exist already. * **Reducer Optimizations:** Optimize performance by batching the serial execution of reduced function calls. * **Parallel Scheduling:** Reduce latency by enabling parallel execution across multiple machines. * **Cyclic Graph Support:** Enable more flexible agentic behaviors by leveraging cycles in graphs. * **Ephemeral Graphs:** Perform multi-stage inference and retrieval without persisting intermediate outputs. * **Data Loader Functions:** Stream values into graphs over time using the `yield` keyword. #### 🛠️ SDK * **TypeScript SDK:** Build an SDK for writing workflows in Typescript. ### Star History [](https://star-history.com/#tensorlakeai/indexify&Date) ### Contributors <a href="https://github.com/tensorlakeai/indexify/graphs/contributors"> <img alt="contributors" src="https://contrib.rocks/image?repo=tensorlakeai/indexify"/> </a> <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;"> <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;"> ↑ Back to Top ↑ </a> </p> ", Assign "at most 3 tags" to the expected json: {"id":"10380","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"