RAGLight is a lightweight and modular Python library for implementing Retrieval-Augmented Generation (RAG). It enhances the capabilities of Large Language Models (LLMs) by combining document retrieval with natural language inference.

Designed for simplicity and flexibility, RAGLight provides modular components to easily integrate various LLMs, embeddings, and vector stores, making it an ideal tool for building context-aware AI solutions.

• Requirements

• Features

• Import library

• Chat with Your Documents Instantly With CLI

  • Ignore Folders Feature
  • Ignore Folders in Configuration Classes

• Deploy as a REST API (raglight serve)

  • Start the server
  • Launch the Chat UI
  • Endpoints
  • Configuration via environment variables
  • Deploy with Docker Compose

• Environment Variables

• Providers and Databases

  • LLM
  • Embeddings
  • Vector Store

• Quick Start

  • Knowledge Base
  • RAG
  • Agentic RAG
  • MCP Integration
  • Use Custom Pipeline
  • Override Default Processors
  • Hybrid Search
  • Query Reformulation
  • Conversation History
  • AWS Bedrock
  • Observability with Langfuse

• Use RAGLight with Docker

  • Build your image
  • Run your image

⚠️ Requirements

Actually RAGLight supports :

• Ollama
• Google Gemini
• LMStudio
• vLLM
• OpenAI API
• Mistral API
• AWS Bedrock

If you use LMStudio, you need to have the model you want to use loaded in LMStudio. If you use AWS Bedrock, configure your AWS credentials (env vars, ~/.aws/credentials, or IAM role) — no extra install needed.

• Embeddings Model Integration: Plug in your preferred embedding models (e.g., HuggingFace all-MiniLM-L6-v2) for compact and efficient vector embeddings.
• LLM Agnostic: Seamlessly integrates with different LLMs from different providers (Ollama, LMStudio, Mistral, OpenAI, Google Gemini, AWS Bedrock).
• RAG Pipeline: Combines document retrieval and language generation in a unified workflow.
• Agentic RAG Pipeline: Use Agent to improve your RAG performances.
• 🔌 MCP Integration: Add external tool capabilities (e.g. code execution, database access) via MCP servers.
• Flexible Document Support: Ingest and index various document types (e.g., PDF, TXT, DOCX, Python, Javascript, ...).
• Extensible Architecture: Easily swap vector stores, embedding models, or LLMs to suit your needs.
• 🔍 Hybrid Search (BM25 + Semantic + RRF): Combine keyword-based BM25 retrieval with dense vector search using Reciprocal Rank Fusion for best-of-both-worlds results.
• ✍️ Query Reformulation: Automatically rewrites follow-up questions into standalone queries using conversation history, improving retrieval accuracy in multi-turn conversations.
• 💬 Conversation History: Full multi-turn history supported across all providers (Ollama, OpenAI, Mistral, LMStudio, Gemini, Bedrock) with optional max_history cap.
• ☁️ AWS Bedrock: Use Claude, Titan, Llama and other Bedrock models for both LLM inference and embeddings.
• 📊 Langfuse Observability (v3+): Trace every RAG call end-to-end — retrieve, rerank, and generate — directly in your Langfuse dashboard.

To install the library, run:

pip install raglight

For the quickest and easiest way to get started, RAGLight provides an interactive command-line wizard. It will guide you through every step, from selecting your documents to chatting with them, without writing a single line of Python. Prerequisite: Ensure you have a local LLM service like Ollama running.

Just run this one command in your terminal:

raglight chat

You can also launch the Agentic RAG wizard with:

raglight agentic-chat

The wizard will guide you through the setup process. Here is what it looks like:

The wizard will ask you for:

• 📂 Data Source: The path to your local folder containing the documents.
• 🚫 Ignore Folders: Configure which folders to exclude during indexing (e.g., .venv, node_modules, __pycache__).
• 💾 Vector Database: Where to store the indexed data and what to name it.
• 🧠 Embeddings Model: Which model to use for understanding your documents.
• 🤖 Language Model (LLM): Which LLM to use for generating answers.

After configuration, it will automatically index your documents and start a chat session.

RAGLight automatically excludes common directories that shouldn't be indexed, such as:

• Virtual environments (.venv, venv, env)
• Node.js dependencies (node_modules)
• Python cache files (__pycache__)
• Build artifacts (build, dist, target)
• IDE files (.vscode, .idea)
• And many more...

You can customize this list during the CLI setup or use the default configuration. This ensures that only relevant code and documentation are indexed, improving performance and reducing noise in your search results.

The ignore folders feature is also available in all configuration classes, allowing you to specify which directories to exclude during indexing:

• RAGConfig: Use ignore_folders parameter to exclude folders during RAG pipeline indexing
• AgenticRAGConfig: Use ignore_folders parameter to exclude folders during AgenticRAG pipeline indexing
• VectorStoreConfig: Use ignore_folders parameter to exclude folders during vector store operations

All configuration classes use Settings.DEFAULT_IGNORE_FOLDERS as the default value, but you can override this with your custom list:

# Example: Custom ignore folders for any configuration
custom_ignore_folders = [
    ".venv",
    "venv",
    "node_modules",
    "__pycache__",
    ".git",
    "build",
    "dist",
    "temp_files",  # Your custom folders
    "cache"
]

# Use in any configuration class
config = RAGConfig(
    llm=Settings.DEFAULT_LLM,
    provider=Settings.OLLAMA,
    ignore_folders=custom_ignore_folders  # Override default
)

See the complete example in examples/ignore_folders_config_example.py for all configuration types.

raglight serve starts a FastAPI server configured entirely via environment variables — no Python code required.

raglight serve

Options :

--host      Host to bind (default: 0.0.0.0)
--port      Port to listen on (default: 8000)
--reload    Enable auto-reload for development (default: false)
--workers   Number of worker processes (default: 1)
--ui        Launch the Streamlit chat UI alongside the API (default: false)
--ui-port   Port for the Streamlit UI (default: 8501)

Example :

RAGLIGHT_LLM_MODEL=mistral-small-latest \
RAGLIGHT_LLM_PROVIDER=Mistral \
raglight serve --port 8080

Langfuse tracing example:

LANGFUSE_HOST=http://localhost:3000 \
LANGFUSE_PUBLIC_KEY=pk-lf-... \
LANGFUSE_SECRET_KEY=sk-lf-... \
raglight serve

Langfuse tracing is enabled automatically when LANGFUSE_HOST (or LANGFUSE_BASE_URL), LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY are all set in the environment. Requires pip install "raglight[langfuse]".

Add --ui to start a Streamlit chat interface alongside the REST API — no extra setup required:

raglight serve --ui

The UI lets you:

• Chat with your documents — full conversation history, markdown rendering
• Upload files directly from the browser (PDF, TXT, code…)
• Ingest a directory by providing a path on the server machine
• Switch LLM on the fly — the sidebar's ⚙️ Model settings panel lets you change provider, model, and API base URL without restarting the server (AWSBedrock and GoogleGemini included)

Use --ui-port to change the Streamlit port:

raglight serve --ui --port 8000 --ui-port 3000

Both processes share the same configuration (env vars) and are terminated together when you stop the server.

The interactive API documentation (Swagger UI) is automatically available at http://localhost:8000/docs.

# Health check
curl http://localhost:8000/health

# Ask a question
curl -X POST http://localhost:8000/generate \
  -H "Content-Type: application/json" \
  -d '{"question": "What is RAGLight?"}'

# Ingest a local folder
curl -X POST http://localhost:8000/ingest \
  -H "Content-Type: application/json" \
  -d '{"data_path": "./my_documents"}'

# Ingest a GitHub repository
curl -X POST http://localhost:8000/ingest \
  -H "Content-Type: application/json" \
  -d '{"github_url": "https://github.com/Bessouat40/RAGLight", "github_branch": "main"}'

# Upload files directly (multipart)
curl -X POST http://localhost:8000/ingest/upload \
  -F "files=@./rapport.pdf" \
  -F "files=@./notes.txt"

# List collections
curl http://localhost:8000/collections

All server settings are read from RAGLIGHT_* environment variables. Copy examples/serve_example/.env.example to .env and adjust the values.

The quickest way to deploy in production :

cd examples/serve_example
cp .env.example .env   # edit values as needed
docker-compose up

The docker-compose.yml uses extra_hosts: host.docker.internal:host-gateway so the container can reach an Ollama instance running on the host machine.

You can set several environment variables to change RAGLight settings :

Provider credentials & URLs

• MISTRAL_API_KEY if you want to use Mistral API
• OLLAMA_CLIENT_URL if you have a custom Ollama URL
• LMSTUDIO_CLIENT if you have a custom LMStudio URL
• OPENAI_CLIENT_URL if you have a custom OpenAI URL or vLLM URL
• OPENAI_API_KEY if you need an OpenAI key
• GEMINI_API_KEY if you need a Google Gemini API key
• AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION for AWS Bedrock (alternatively use ~/.aws/credentials or an IAM role)

REST API server (raglight serve)

See the full list in the Configuration via environment variables section above.

For your LLM inference, you can use these providers :

• LMStudio (Settings.LMSTUDIO)
• Ollama (Settings.OLLAMA)
• Mistral API (Settings.MISTRAL)
• vLLM (Settings.VLLM)
• OpenAI (Settings.OPENAI)
• Google Gemini (Settings.GOOGLE_GEMINI)
• AWS Bedrock (Settings.AWS_BEDROCK)

For embeddings models, you can use these providers :

• Huggingface (Settings.HUGGINGFACE)
• Ollama (Settings.OLLAMA)
• vLLM (Settings.VLLM)
• OpenAI (Settings.OPENAI)
• Google Gemini (Settings.GOOGLE_GEMINI)
• AWS Bedrock (Settings.AWS_BEDROCK)

For your vector store, you can use :

• Chroma (Settings.CHROMA)

Knowledge Base is a way to define data you want to ingest inside your vector store during the initialization of your RAG. It's the data ingest when you call build function :

from raglight import RAGPipeline
pipeline = RAGPipeline(knowledge_base=[
    FolderSource(path="<path to your folder with pdf>/knowledge_base"),
    GitHubSource(url="https://github.com/Bessouat40/RAGLight")
    ],
    model_name="llama3",
    provider=Settings.OLLAMA,
    k=5)

pipeline.build()

You can define two different knowledge base :

1. Folder Knowledge Base

All files/folders into this directory will be ingested inside the vector store :

from raglight import FolderSource
FolderSource(path="<path to your folder with pdf>/knowledge_base"),

2. Github Knowledge Base

You can declare Github Repositories you want to store into your vector store :

from raglight import GitHubSource
GitHubSource(url="https://github.com/Bessouat40/RAGLight")

You can setup easily your RAG with RAGLight :

from raglight.rag.simple_rag_api import RAGPipeline
from raglight.models.data_source_model import FolderSource, GitHubSource
from raglight.config.settings import Settings
from raglight.config.rag_config import RAGConfig
from raglight.config.vector_store_config import VectorStoreConfig

Settings.setup_logging()

knowledge_base=[
    FolderSource(path="<path to your folder with pdf>/knowledge_base"),
    GitHubSource(url="https://github.com/Bessouat40/RAGLight")
    ]

vector_store_config = VectorStoreConfig(
    embedding_model = Settings.DEFAULT_EMBEDDINGS_MODEL,
    api_base = Settings.DEFAULT_OLLAMA_CLIENT,
    provider=Settings.HUGGINGFACE,
    database=Settings.CHROMA,
    persist_directory = './defaultDb',
    collection_name = Settings.DEFAULT_COLLECTION_NAME
)

config = RAGConfig(
        llm = Settings.DEFAULT_LLM,
        provider = Settings.OLLAMA,
        # k = Settings.DEFAULT_K,
        # cross_encoder_model = Settings.DEFAULT_CROSS_ENCODER_MODEL,
        # system_prompt = Settings.DEFAULT_SYSTEM_PROMPT,
        # knowledge_base = knowledge_base
    )

pipeline = RAGPipeline(config, vector_store_config)

pipeline.build()

response = pipeline.generate("How can I create an easy RAGPipeline using raglight framework ? Give me python implementation")
print(response)

You just have to fill the model you want to use.

⚠️ By default, LLM Provider will be Ollama

This pipeline extends the Retrieval-Augmented Generation (RAG) concept by incorporating an additional Agent. This agent can retrieve data from your vector store.

You can modify several parameters in your config :

• provider : Your LLM Provider (Ollama, LMStudio, Mistral)
• model : The model you want to use
• k : The number of document you'll retrieve
• max_steps : Max reflexion steps used by your Agent
• api_key : Your Mistral API key
• api_base : Your API URL (Ollama URL, LM Studio URL, ...)
• num_ctx : Your context max_length
• verbosity_level : Your logs' verbosity level
• ignore_folders : List of folders to exclude during indexing (e.g., [".venv", "node_modules", "pycache"])

from raglight.config.settings import Settings
from raglight.rag.simple_agentic_rag_api import AgenticRAGPipeline
from raglight.config.agentic_rag_config import AgenticRAGConfig
from raglight.config.vector_store_config import VectorStoreConfig
from raglight.config.settings import Settings
from dotenv import load_dotenv

load_dotenv()
Settings.setup_logging()

persist_directory = './defaultDb'
model_embeddings = Settings.DEFAULT_EMBEDDINGS_MODEL
collection_name = Settings.DEFAULT_COLLECTION_NAME

vector_store_config = VectorStoreConfig(
    embedding_model = model_embeddings,
    api_base = Settings.DEFAULT_OLLAMA_CLIENT,
    database=Settings.CHROMA,
    persist_directory = persist_directory,
    # host='localhost',
    # port='8001',
    provider = Settings.HUGGINGFACE,
    collection_name = collection_name
)

# Custom ignore folders - you can override the default list
custom_ignore_folders = [
    ".venv",
    "venv",
    "node_modules",
    "__pycache__",
    ".git",
    "build",
    "dist",
    "my_custom_folder_to_ignore"  # Add your custom folders here
]

config = AgenticRAGConfig(
            provider = Settings.MISTRAL,
            model = "mistral-large-2411",
            k = 10,
            system_prompt = Settings.DEFAULT_AGENT_PROMPT,
            max_steps = 4,
            api_key = Settings.MISTRAL_API_KEY, # os.environ.get('MISTRAL_API_KEY')
            ignore_folders = custom_ignore_folders,  # Use custom ignore folders
            # api_base = ... # If you have a custom client URL
            # num_ctx = ... # Max context length
            # verbosity_level = ... # Default = 2
            # knowledge_base = knowledge_base
        )

agenticRag = AgenticRAGPipeline(config, vector_store_config)
agenticRag.build()

response = agenticRag.generate("Please implement for me AgenticRAGPipeline inspired by RAGPipeline and AgenticRAG and RAG")

print('response : ', response)

RAGLight supports MCP Server integration to enhance the reasoning capabilities of your agent. MCP allows the agent to interact with external tools (e.g., code execution environments, database tools, or search agents) via a standardized server interface.

To use MCP, simply pass a mcp_config parameter to your AgenticRAGConfig, where each config defines the url (and optionally transport) of the MCP server.

Just add this parameter to your AgenticRAGPipeline :

config = AgenticRAGConfig(
    provider = Settings.OPENAI,
    model = "gpt-4o",
    k = 10,
    mcp_config = [
        {"url": "http://127.0.0.1:8001/sse"}  # Your MCP server URL
    ],
    ...
)

📚 Documentation: Learn how to configure and launch an MCP server using MCPClient.server_parameters

1. Configure Your Pipeline

You can also setup your own Pipeline :

from raglight.rag.builder import Builder
from raglight.config.settings import Settings

rag = Builder() \
    .with_embeddings(Settings.HUGGINGFACE, model_name=model_embeddings) \
    .with_vector_store(Settings.CHROMA, persist_directory=persist_directory, collection_name=collection_name) \
    .with_llm(Settings.OLLAMA, model_name=model_name, system_prompt_file=system_prompt_directory, provider=Settings.LMStudio) \
    .build_rag(k = 5)

2. Ingest Documents Inside Your Vector Store

Then you can ingest data into your vector store.

1. You can use default pipeline that'll ingest no code data :

rag.vector_store.ingest(data_path='./data')

2. Or you can use code pipeline :

rag.vector_store.ingest(repos_path=['./repository1', './repository2'])

This pipeline will ingest code embeddings into your collection : collection_name. But this pipeline will also extract all signatures from your code base and ingest it into : collection_name_classes.

You have access to two different functions inside VectorStore class : similarity_search and similarity_search_class to search into different collection.

3. Query the Pipeline

Retrieve and generate answers using the RAG pipeline:

response = rag.generate("How can I optimize my marathon training?")
print(response)

✚ More Examples

You can find more examples for all these use cases in the examples directory.

RAGLight ships with built-in document processors based on file extension:

• pdf → PDFProcessor
• py, js, ts, java, cpp, cs → CodeProcessor
• txt, md, html → TextProcessor

You can override these defaults using the custom_processors argument when building your vector store. This is especially useful if you want to handle certain file types with a custom logic, such as using a Vision-Language Model (VLM) for PDFs with diagrams and images. RAGLight provides a VLM based Processor too.

from raglight.document_processing.vlm_pdf_processor import VlmPDFProcessor
from raglight.llm.ollama_model import OllamaModel
from raglight.rag.builder import Builder
from raglight.config.settings import Settings

from dotenv import load_dotenv
import os

load_dotenv()
Settings.setup_logging()

persist_directory = './defaultDb'
model_embeddings = Settings.DEFAULT_EMBEDDINGS_MODEL
collection_name = Settings.DEFAULT_COLLECTION_NAME
data_path = os.environ.get('DATA_PATH')

# Vision-Language Model (example with Ollama)
vlm = OllamaModel(
    model_name="ministral-3:3b",
    system_prompt="You are a technical documentation visual assistant.",
)

custom_processors = {
    "pdf": VlmPDFProcessor(vlm),  # Override default PDF processor
}

vector_store = Builder() \
    .with_embeddings(Settings.HUGGINGFACE, model_name=model_embeddings) \
    .with_vector_store(
        Settings.CHROMA,
        persist_directory=persist_directory,
        collection_name=collection_name,
        custom_processors=custom_processors,
    ) \
    .build_vector_store()

vector_store.ingest(data_path=data_path)

With this setup, all .pdf files will be processed by your custom VlmPDFProcessor, while other file types keep using the default processors.

RAGLight supports three retrieval strategies, configurable via the search_type parameter:

from raglight.rag.builder import Builder
from raglight.config.settings import Settings

rag = (
    Builder()
    .with_embeddings(Settings.HUGGINGFACE, model_name="all-MiniLM-L6-v2")
    .with_vector_store(
        Settings.CHROMA,
        persist_directory="./myDb",
        collection_name="my_collection",
        search_type=Settings.SEARCH_HYBRID,  # "semantic" | "bm25" | "hybrid"
        alpha=0.5,                           # weight between semantic and BM25 in RRF
    )
    .with_llm(Settings.OLLAMA, model_name="llama3.1:8b")
    .build_rag(k=5)
)

rag.vector_store.ingest(data_path="./docs")
response = rag.generate("What is Reciprocal Rank Fusion?")
print(response)

from raglight.rag.simple_rag_api import RAGPipeline
from raglight.config.rag_config import RAGConfig
from raglight.config.vector_store_config import VectorStoreConfig
from raglight.config.settings import Settings
from raglight.models.data_source_model import FolderSource

vector_store_config = VectorStoreConfig(
    embedding_model=Settings.DEFAULT_EMBEDDINGS_MODEL,
    provider=Settings.HUGGINGFACE,
    database=Settings.CHROMA,
    persist_directory="./myDb",
    collection_name="my_collection",
    search_type=Settings.SEARCH_HYBRID,   # or SEARCH_SEMANTIC / SEARCH_BM25
    hybrid_alpha=0.5,
)

config = RAGConfig(
    llm="llama3.1:8b",
    provider=Settings.OLLAMA,
    k=5,
    knowledge_base=[FolderSource(path="./docs")],
)

pipeline = RAGPipeline(config, vector_store_config)
pipeline.build()
response = pipeline.generate("Explain the retrieval pipeline")
print(response)

How RRF works: each search mode returns its own ranked list of documents. RRF assigns a score of 1 / (k + rank) to each document per list and sums them — documents appearing high in both lists are promoted, while documents unique to one list are kept but ranked lower. This gives the hybrid mode better recall and precision than either mode alone.

See the full working example in examples/hybrid_search_example.py.

RAGLight automatically rewrites follow-up questions into standalone queries before retrieval. This dramatically improves accuracy in multi-turn conversations where the user's question references previous context (e.g. "and for Python?" → "How do I do X in Python?").

Reformulation is enabled by default. The current LLM is used to rewrite the question; if there is no conversation history yet, the question is passed through unchanged.

from raglight.config.rag_config import RAGConfig
from raglight.config.settings import Settings

# Enabled by default
config = RAGConfig(
    llm=Settings.DEFAULT_LLM,
    provider=Settings.OLLAMA,
)

# Disable if needed
config = RAGConfig(
    llm=Settings.DEFAULT_LLM,
    provider=Settings.OLLAMA,
    reformulation=False,
)

from raglight.rag.builder import Builder
from raglight.config.settings import Settings

rag = (
    Builder()
    .with_embeddings(Settings.HUGGINGFACE, model_name="all-MiniLM-L6-v2")
    .with_vector_store(Settings.CHROMA, persist_directory="./myDb", collection_name="my_collection")
    .with_llm(Settings.OLLAMA, model_name="llama3.1:8b")
    .build_rag(k=5, reformulation=True)  # True by default
)

The reformulated question is logged at INFO level so you can inspect what the LLM produced.

Pipeline with reformulation enabled:

reformulate → retrieve → [rerank?] → generate

RAGLight automatically maintains conversation history across generate() calls. Each turn appends a user and an assistant message passed to the LLM on the next call — enabling genuine multi-turn conversations across all providers.

By default, history is capped at 20 messages (~10 turns). Use max_history to adjust this limit, or pass None for unlimited history:

# Via RAGConfig (high-level API)
config = RAGConfig(
    llm=Settings.DEFAULT_LLM,
    provider=Settings.OLLAMA,
    max_history=20,  # keep last 20 messages (~10 turns)
)

# Via Builder
rag = (
    Builder()
    .with_embeddings(Settings.HUGGINGFACE, model_name="all-MiniLM-L6-v2")
    .with_vector_store(Settings.CHROMA, persist_directory="./myDb", collection_name="col")
    .with_llm(Settings.OLLAMA, model_name="llama3.1:8b")
    .build_rag(k=5, max_history=20)
)

Tip: set max_history to roughly 2× the number of turns you want to retain (each turn = 2 messages).

RAGLight supports AWS Bedrock for both LLM inference and embeddings. Authentication relies on the standard boto3 credential chain (env vars, ~/.aws/credentials, or IAM role).

AWS credentials (one of):

• Environment variables: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION
• AWS credentials file: ~/.aws/credentials
• IAM role (EC2 / ECS / Lambda)

Supported models (examples):

from raglight.rag.simple_rag_api import RAGPipeline
from raglight.config.settings import Settings
from raglight.config.rag_config import RAGConfig
from raglight.config.vector_store_config import VectorStoreConfig
from raglight.models.data_source_model import GitHubSource

Settings.setup_logging()

vector_store_config = VectorStoreConfig(
    provider=Settings.AWS_BEDROCK,
    embedding_model=Settings.AWS_BEDROCK_EMBEDDING_MODEL,  # amazon.titan-embed-text-v2:0
    database=Settings.CHROMA,
    persist_directory="./bedrockDb",
    collection_name="bedrock_collection",
)

config = RAGConfig(
    provider=Settings.AWS_BEDROCK,
    llm=Settings.AWS_BEDROCK_LLM_MODEL,  # anthropic.claude-3-5-sonnet-20241022-v2:0
    knowledge_base=[GitHubSource(url="https://github.com/Bessouat40/RAGLight")],
)

pipeline = RAGPipeline(config, vector_store_config)
pipeline.build()
response = pipeline.generate("How can I create a RAGPipeline using raglight?")
print(response)

See the full working example in examples/bedrock_example.py.

RAGLight supports Langfuse 4.0.0 for full observability of your RAG pipeline. Every generate() call is traced as a single Langfuse trace, with each LangGraph node (retrieve, rerank, generate) appearing as a separate span.

pip install "raglight[langfuse]"
# or directly:
pip install "langfuse==4.0.0"

from raglight.config.rag_config import RAGConfig
from raglight.config.vector_store_config import VectorStoreConfig
from raglight.config.langfuse_config import LangfuseConfig
from raglight.config.settings import Settings
from raglight.rag.simple_rag_api import RAGPipeline

langfuse_config = LangfuseConfig(
    public_key="pk-lf-...",
    secret_key="sk-lf-...",
    host="http://localhost:3000",  # or your Langfuse Cloud URL
)

config = RAGConfig(
    llm=Settings.DEFAULT_LLM,
    provider=Settings.OLLAMA,
    langfuse_config=langfuse_config,
)

vector_store_config = VectorStoreConfig(
    embedding_model=Settings.DEFAULT_EMBEDDINGS_MODEL,
    provider=Settings.HUGGINGFACE,
    database=Settings.CHROMA,
    persist_directory="./myDb",
    collection_name="my_collection",
)

pipeline = RAGPipeline(config, vector_store_config)
pipeline.build()
response = pipeline.generate("What is RAGLight?")
print(response)

from raglight.rag.builder import Builder
from raglight.config.langfuse_config import LangfuseConfig
from raglight.config.settings import Settings

langfuse_config = LangfuseConfig(
    public_key="pk-lf-...",
    secret_key="sk-lf-...",
    host="http://localhost:3000",
)

rag = (
    Builder()
    .with_embeddings(Settings.HUGGINGFACE, model_name=Settings.DEFAULT_EMBEDDINGS_MODEL)
    .with_vector_store(Settings.CHROMA, persist_directory="./myDb", collection_name="my_collection")
    .with_llm(Settings.OLLAMA, model_name=Settings.DEFAULT_LLM)
    .build_rag(k=5, langfuse_config=langfuse_config)
)

rag.vector_store.ingest(data_path="./docs")
response = rag.generate("Explain the retrieval pipeline")
print(response)

By default, a UUID is generated once per RAG instance and reused for every generate() call, so all turns of the same conversation are grouped under the same Langfuse trace.

You can pin a custom ID via LangfuseConfig(session_id="my-session-42", ...).

You can use RAGLight inside a Docker container easily. Find Dockerfile example here : examples/Dockerfile.example

Just go to examples directory and run :

docker build -t docker-raglight -f Dockerfile.example .

In order your container can communicate with Ollama or LMStudio, you need to add a custom host-to-IP mapping :

docker run --add-host=host.docker.internal:host-gateway docker-raglight

We use --add-host flag to allow Ollama call.