qdrant

command

v1.0.0 Latest Latest Go to latest Published: Jul 14, 2026 License: Apache-2.0 Imports: 9 Imported by: 0

Details

Valid go.mod file
Redistributable license
Tagged version
Stable version
Learn more about best practices

Repository

github.com/bzdvdn/draftrag

Links

Open Source Insights

README ¶

Qdrant — RAG with Qdrant

Interactive RAG chat with Qdrant as a vector store. Creates the collection automatically on first run.

Quick start

1. Start Qdrant:

docker compose up -d

2. Run the example:

cd examples/qdrant && cp .env.example .env && go run .

For mock mode this is sufficient. For a real LLM, set LLM_PROVIDER=ollama|openai|anthropic and the corresponding keys.

Environment variables

Variable	Default	Description
`LLM_PROVIDER`	`mock`	LLM provider (`mock`, `ollama`, `openai`, `anthropic`)
`EMBEDDING_DIM`	`1536`	Vector dimension
`QDRANT_URL`	`http://localhost:6333`	Qdrant server URL
`COLLECTION_NAME`	`draftrag_chunks`	Collection name

For LLM_PROVIDER=ollama:

Variable	Default	Description
`OLLAMA_HOST`	`http://localhost:11434`	Ollama URL
`OLLAMA_EMBED_MODEL`	`nomic-embed-text`	Embedding model
`OLLAMA_LLM_MODEL`	`llama3.2`	LLM model

For LLM_PROVIDER=openai:

Variable	Default	Description
`OPENAI_API_KEY`	—	Required. API key
`OPENAI_BASE_URL`	`https://api.openai.com`	Base URL
`OPENAI_EMBED_MODEL`	`text-embedding-3-small`	Embedding model
`OPENAI_LLM_MODEL`	`gpt-4o-mini`	LLM model

For LLM_PROVIDER=anthropic:

Variable	Default	Description
`ANTHROPIC_API_KEY`	—	Required. API key
`ANTHROPIC_LLM_MODEL`	`claude-3-5-sonnet-latest`	LLM model

Documentation ¶

Overview ¶

@sk-task docs-and-examples#T2.3: qdrant example — RAG-чат с Qdrant (AC-002). Использует публичный API draftrag напрямую. Shared только для mock/print.

Быстрый старт с Docker:

docker compose up -d
cp .env.example .env && go run .

Source Files ¶

View all Source files

main.go

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL