mirror of https://github.com/magnus919/agent-skills.git synced 2026-09-22 00:56:35 +03:00

Files

T

Magnus Hedemark 3e86349539 feat: add llamaindex — expert skill for LlamaIndex framework

Comprehensive skill covering:
- Core architecture (7 primitives, Settings, data flow)
- RAG strategies (basic through advanced with hybrid retrieval, reranking)
- Multi-agent orchestration (AgentWorkflow, handoff bug fix)
- Event-driven workflows (durable execution, checkpoint/resume)
- Production deployment (llama-deploy, debugging, observability)
- PropertyGraphIndex (knowledge graphs, hybrid retrieval)
- Evaluation and span-attached observability
- Integration ecosystem (vector stores, LlamaHub, LlamaParse)

9 reference files, 4 templates, 1 verification script.
MIT licensed. 100% AI agent portable (no platform-specific content).

Signed-off-by: Magnus Hedemark <magnus919@pm.me>

2026-07-09 13:32:53 -04:00

2.2 KiB

Raw Blame History

LlamaIndex Core Architecture

Seven Core Primitives

LlamaIndex organizes functionality around seven primitives that map to RAG pipeline stages:

Primitive	Purpose	Example
Reader	Pull data from sources	`SimpleDirectoryReader("./data")`
Document	Source content with metadata	Returned by Reader
Node	Chunk of a Document	Created by Node Parsers
Index	Data structure over Nodes	`VectorStoreIndex`, `PropertyGraphIndex`
Retriever	Return relevant Nodes	`index.as_retriever(similarity_top_k=5)`
Query Engine	Retriever + response synthesis	`index.as_query_engine()`
Agent	LLM with tools	`FunctionAgent(tools=[...])`
Workflow	Event-driven orchestration	`class MyFlow(Workflow)`

Configuration

The Settings object provides global configuration, replacing the deprecated ServiceContext:

from llama_index.core import Settings
from llama_index.llms.openai import OpenAI

Settings.llm = OpenAI(model="gpt-4o")
Settings.embed_model = "local:BAAI/bge-small-en-v1.5"
Settings.text_splitter = SentenceSplitter(chunk_size=1024, chunk_overlap=20)

Data Flow

Source -> Reader -> Document -> Node Parser -> Nodes -> Index
                                                            |
                                           Retriever <- Query Engine <- Agent
                                                               |
                                                          Response

Workflow Event Model

Workflows replace DAG-based composition with typed event passing:

from llama_index.core.workflow import Workflow, StartEvent, StopEvent, Event, step

class RetrievedEvent(Event):
    query: str
    nodes: list

class SimpleRAG(Workflow):
    @step
    async def retrieve(self, ev: StartEvent) -> RetrievedEvent:
        # ... retrieval logic
        return RetrievedEvent(query=ev.query, nodes=nodes)

    @step
    async def generate(self, ev: RetrievedEvent) -> StopEvent:
        # ... generation logic
        return StopEvent(result=str(resp))

Steps infer input/output types from annotations. The framework validates the event graph before execution.

2.2 KiB Raw Blame History