# Langbase Python SDK
[](https://badge.fury.io/py/langbase)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/Apache-2.0)
The official Python SDK for [Langbase](https://langbase.com) - Build declarative and composable AI-powered LLM products with ease.
## Documentation
Check the [Langbase SDK documentation](https://langbase.com/docs/sdk) for more details.
The following examples are for reference only. Prefer docs for the latest information.
## Features
- **Simple and intuitive API** - Get started in minutes
- **Streaming support** - Real-time text generation with typed events
- **Type safety** - Full type hints for better IDE support
- **Minimal dependencies** - Only what you need
- **Python 3.7+** - Support for modern Python versions
## Installation
Install Langbase SDK:
```bash
pip install langbase
```
Install dotenv:
```bash
pip install dotenv
```
## Quick Start
### 1. Set up your API key
Create a `.env` file and add your [Langbase API Key](https://langbase.com/docs/api-reference/api-keys).
```bash
LANGBASE_API_KEY="your-api-key"
LLM_API_KEY="your-llm-api-key"
```
---
### 2. Initialize the client
```python
from langbase import Langbase
import os
from dotenv import load_dotenv
load_dotenv()
# Get API key from environment variable
langbase_api_key = os.getenv("LANGBASE_API_KEY")
llm_api_key = os.getenv("LLM_API_KEY")
# Initialize the client
langbase = Langbase(api_key=langbase_api_key)
langbase = Langbase(api_key=langbase_api_key)
```
### 3. Generate text
```python
# Simple generation
response = langbase.agent.run(
input=[{"role": "user", "content": "Tell me about AI"}],
model="openai:gpt-4.1-mini",
api_key=llm_api_key,
)
print(response["output"])
```
---
### 4. Stream text (Simple)
```python
form langbase import get_runner
# Stream text as it's generated
response = langbase.agent.run(
input=[{"role": "user", "content": "Tell me about AI"}],
model="openai:gpt-4.1-mini",
api_key=llm_api_key,
stream=True,
)
runner = get_runner(response)
for content in runner.text_generator():
print(content, end="", flush=True)
```
### 5. Stream with typed events (Advanced)
```python
from langbase import StreamEventType, get_typed_runner
response = langbase.agent.run(
input=[{"role": "user", "content": "What is an AI Engineer?"}],
model="openai:gpt-4.1-mini",
api_key=llm_api_key,
stream=True,
)
# Create typed stream processor
runner = get_typed_runner(response)
# Register event handlers
runner.on(
StreamEventType.CONNECT,
lambda event: print(f"✓ Connected! Thread ID: {event['threadId']}\n"),
)
runner.on(
StreamEventType.CONTENT,
lambda event: print(event["content"], end="", flush=True),
)
runner.on(
StreamEventType.TOOL_CALL,
lambda event: print(
f"\n🔧 Tool call: {event['toolCall']['function']['name']}"
),
)
runner.on(
StreamEventType.COMPLETION,
lambda event: print(f"\n\n✓ Completed! Reason: {event['reason']}"),
)
runner.on(
StreamEventType.ERROR,
lambda event: print(f"\n❌ Error: {event['message']}"),
)
runner.on(
StreamEventType.END,
lambda event: print(f"⏱️ Total duration: {event['duration']:.2f}s"),
)
# Process the stream
runner.process()
```
## Core Features
### Pipes - AI Pipeline Execution
```python
# List all pipes
pipes = langbase.pipes.list()
# Run a pipe
response = langbase.pipes.run(
name="ai-agent",
messages=[{"role": "user", "content": "Hello!"}],
variables={"style": "friendly"}, # Optional variables
stream=True, # Enable streaming
)
```
### Memory - Persistent Context Storage
```python
# Create a memory
memory = langbase.memories.create(
name="product-docs",
description="Product documentation",
)
# Upload documents
langbase.memories.documents.upload(
memory_name="product-docs",
document_name="guide.pdf",
document=open("guide.pdf", "rb"),
content_type="application/pdf",
)
# Retrieve relevant context
results = langbase.memories.retrieve(
query="How do I get started?",
memory=[{"name": "product-docs"}],
top_k=3,
)
```
### Agent - LLM Agent Execution
```python
# Run an agent with tools
response = langbase.agent.run(
response = langbase.agent.run(
model="openai:gpt-4",
messages=[{"role": "user", "content": "Search for AI news"}],
tools=[{"type": "function", "function": {...}}],
tool_choice="auto",
api_key="your-llm-api-key",
stream=True,
)
```
### Tools - Built-in Utilities
```python
# Chunk text for processing
chunks = langbase.chunker(
chunks = langbase.chunker(
content="Long text to split...",
chunk_max_length=1024,
chunk_overlap=256,
)
# Generate embeddings
embeddings = langbase.embed(
embeddings = langbase.embed(
chunks=["Text 1", "Text 2"],
embedding_model="openai:text-embedding-3-small",
)
# Parse documents
content = langbase.parser(
content = langbase.parser(
document=open("document.pdf", "rb"),
document_name="document.pdf",
content_type="application/pdf",
)
```
## Examples
Explore the [examples](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples) directory for complete working examples:
- [Generate text](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/agent/agent.run.py)
- [Stream text](https://github.com/LangbaseInc/langbase-python-sdk/blob/main/examples/agent/agent.run.stream.py)
- [Work with memory](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/memory/)
- [Agent with tools](https://github.com/LangbaseInc/langbase-python-sdk/blob/main/examples/agent/agent.run.tool.py)
- [Document processing](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/parser/)
- [Workflow automation](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/workflow/)
## SDK Reference
For detailed SDK documentation, visit [langbase.com/docs/sdk](https://langbase.com/docs/sdk).
## Contributing
We welcome contributions! Please see our [Contributing Guide](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/CONTRIBUTING.md) for details.
## Support
- [Documentation](https://langbase.com/docs)
- [Discord Community](https://langbase.com/discord)
- [Issue Tracker](https://github.com/LangbaseInc/langbase-python-sdk/issues)
## License
See the [LICENSE](https://github.com/LangbaseInc/langbase-python-sdk/blob/main/LICENCE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "langbase",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "ai, langbase, agent, memory, rag, mcp, pipes, workflow, llms",
"author": null,
"author_email": "Ahmad Awais <aa@ahmadawais.com>, Ahmad Bilal <bilal@langbase.com>, Ashar Irfan <ashar@langbase.com>, Saad Irfan <saad@langbase.com>, Ankit Kumar <ankit@langbase.com>, Saqib Ameen <saqib@langbase.com>",
"download_url": "https://files.pythonhosted.org/packages/27/a3/e0e0faed11be69990066dc932bc49bf3875bed7f1aa2ee2bcdb193cdd5f3/langbase-0.0.3.tar.gz",
"platform": null,
"description": "# Langbase Python SDK\n\n[](https://badge.fury.io/py/langbase)\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/Apache-2.0)\n\nThe official Python SDK for [Langbase](https://langbase.com) - Build declarative and composable AI-powered LLM products with ease.\n\n## Documentation\n\nCheck the [Langbase SDK documentation](https://langbase.com/docs/sdk) for more details.\n\nThe following examples are for reference only. Prefer docs for the latest information.\n\n## Features\n\n- **Simple and intuitive API** - Get started in minutes\n- **Streaming support** - Real-time text generation with typed events\n- **Type safety** - Full type hints for better IDE support\n- **Minimal dependencies** - Only what you need\n- **Python 3.7+** - Support for modern Python versions\n\n## Installation\n\nInstall Langbase SDK:\n\n```bash\npip install langbase\n```\n\nInstall dotenv:\n\n```bash\npip install dotenv\n```\n\n## Quick Start\n\n### 1. Set up your API key\n\nCreate a `.env` file and add your [Langbase API Key](https://langbase.com/docs/api-reference/api-keys).\n\n```bash\nLANGBASE_API_KEY=\"your-api-key\"\nLLM_API_KEY=\"your-llm-api-key\"\n```\n\n---\n\n### 2. Initialize the client\n\n```python\nfrom langbase import Langbase\nimport os\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\n# Get API key from environment variable\nlangbase_api_key = os.getenv(\"LANGBASE_API_KEY\")\nllm_api_key = os.getenv(\"LLM_API_KEY\")\n\n# Initialize the client\nlangbase = Langbase(api_key=langbase_api_key)\nlangbase = Langbase(api_key=langbase_api_key)\n```\n\n### 3. Generate text\n\n```python\n# Simple generation\nresponse = langbase.agent.run(\n input=[{\"role\": \"user\", \"content\": \"Tell me about AI\"}],\n model=\"openai:gpt-4.1-mini\",\n api_key=llm_api_key,\n)\n\nprint(response[\"output\"])\n```\n\n---\n\n### 4. Stream text (Simple)\n\n```python\nform langbase import get_runner\n\n# Stream text as it's generated\nresponse = langbase.agent.run(\n input=[{\"role\": \"user\", \"content\": \"Tell me about AI\"}],\n model=\"openai:gpt-4.1-mini\",\n api_key=llm_api_key,\n stream=True,\n)\n\nrunner = get_runner(response)\n\nfor content in runner.text_generator():\n print(content, end=\"\", flush=True)\n```\n\n### 5. Stream with typed events (Advanced)\n\n```python\nfrom langbase import StreamEventType, get_typed_runner\n\nresponse = langbase.agent.run(\n input=[{\"role\": \"user\", \"content\": \"What is an AI Engineer?\"}],\n model=\"openai:gpt-4.1-mini\",\n api_key=llm_api_key,\n stream=True,\n)\n\n# Create typed stream processor\nrunner = get_typed_runner(response)\n\n# Register event handlers\nrunner.on(\n StreamEventType.CONNECT,\n lambda event: print(f\"\u2713 Connected! Thread ID: {event['threadId']}\\n\"),\n)\n\nrunner.on(\n StreamEventType.CONTENT,\n lambda event: print(event[\"content\"], end=\"\", flush=True),\n)\n\nrunner.on(\n StreamEventType.TOOL_CALL,\n lambda event: print(\n f\"\\n\ud83d\udd27 Tool call: {event['toolCall']['function']['name']}\"\n ),\n)\n\nrunner.on(\n StreamEventType.COMPLETION,\n lambda event: print(f\"\\n\\n\u2713 Completed! Reason: {event['reason']}\"),\n)\n\nrunner.on(\n StreamEventType.ERROR,\n lambda event: print(f\"\\n\u274c Error: {event['message']}\"),\n)\n\nrunner.on(\n StreamEventType.END,\n lambda event: print(f\"\u23f1\ufe0f Total duration: {event['duration']:.2f}s\"),\n)\n\n# Process the stream\nrunner.process()\n```\n\n## Core Features\n\n### Pipes - AI Pipeline Execution\n\n```python\n# List all pipes\npipes = langbase.pipes.list()\n\n# Run a pipe\nresponse = langbase.pipes.run(\n name=\"ai-agent\",\n messages=[{\"role\": \"user\", \"content\": \"Hello!\"}],\n variables={\"style\": \"friendly\"}, # Optional variables\n stream=True, # Enable streaming\n)\n```\n\n### Memory - Persistent Context Storage\n\n```python\n# Create a memory\nmemory = langbase.memories.create(\n name=\"product-docs\",\n description=\"Product documentation\",\n)\n\n# Upload documents\nlangbase.memories.documents.upload(\n memory_name=\"product-docs\",\n document_name=\"guide.pdf\",\n document=open(\"guide.pdf\", \"rb\"),\n content_type=\"application/pdf\",\n)\n\n# Retrieve relevant context\nresults = langbase.memories.retrieve(\n query=\"How do I get started?\",\n memory=[{\"name\": \"product-docs\"}],\n top_k=3,\n)\n```\n\n### Agent - LLM Agent Execution\n\n```python\n# Run an agent with tools\nresponse = langbase.agent.run(\nresponse = langbase.agent.run(\n model=\"openai:gpt-4\",\n messages=[{\"role\": \"user\", \"content\": \"Search for AI news\"}],\n tools=[{\"type\": \"function\", \"function\": {...}}],\n tool_choice=\"auto\",\n api_key=\"your-llm-api-key\",\n stream=True,\n)\n```\n\n### Tools - Built-in Utilities\n\n```python\n# Chunk text for processing\nchunks = langbase.chunker(\nchunks = langbase.chunker(\n content=\"Long text to split...\",\n chunk_max_length=1024,\n chunk_overlap=256,\n)\n\n# Generate embeddings\nembeddings = langbase.embed(\nembeddings = langbase.embed(\n chunks=[\"Text 1\", \"Text 2\"],\n embedding_model=\"openai:text-embedding-3-small\",\n)\n\n# Parse documents\ncontent = langbase.parser(\ncontent = langbase.parser(\n document=open(\"document.pdf\", \"rb\"),\n document_name=\"document.pdf\",\n content_type=\"application/pdf\",\n)\n```\n\n## Examples\n\nExplore the [examples](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples) directory for complete working examples:\n\n- [Generate text](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/agent/agent.run.py)\n- [Stream text](https://github.com/LangbaseInc/langbase-python-sdk/blob/main/examples/agent/agent.run.stream.py)\n- [Work with memory](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/memory/)\n- [Agent with tools](https://github.com/LangbaseInc/langbase-python-sdk/blob/main/examples/agent/agent.run.tool.py)\n- [Document processing](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/parser/)\n- [Workflow automation](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/examples/workflow/)\n\n## SDK Reference\n\nFor detailed SDK documentation, visit [langbase.com/docs/sdk](https://langbase.com/docs/sdk).\n\n## Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](https://github.com/LangbaseInc/langbase-python-sdk/tree/main/CONTRIBUTING.md) for details.\n\n## Support\n\n- [Documentation](https://langbase.com/docs)\n- [Discord Community](https://langbase.com/discord)\n- [Issue Tracker](https://github.com/LangbaseInc/langbase-python-sdk/issues)\n\n## License\n\nSee the [LICENSE](https://github.com/LangbaseInc/langbase-python-sdk/blob/main/LICENCE) file for details.\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Python SDK for the Langbase API",
"version": "0.0.3",
"project_urls": {
"Documentation": "https://docs.langbase.com",
"Homepage": "https://langbase.com",
"Issues": "https://github.com/LangbaseInc/langbase-python-sdk/issues",
"Repository": "https://github.com/LangbaseInc/langbase-python-sdk"
},
"split_keywords": [
"ai",
" langbase",
" agent",
" memory",
" rag",
" mcp",
" pipes",
" workflow",
" llms"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "29e6c5b37f025febbc8e3c4cad4ea1783f139178fbb4888e1f089a9ed6cd3efd",
"md5": "3225c719428aa891567717d25573b970",
"sha256": "9f2510b37778c84507614a960021015e82613018442f75aa91068a383155c257"
},
"downloads": -1,
"filename": "langbase-0.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3225c719428aa891567717d25573b970",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 34454,
"upload_time": "2025-08-07T00:37:18",
"upload_time_iso_8601": "2025-08-07T00:37:18.165866Z",
"url": "https://files.pythonhosted.org/packages/29/e6/c5b37f025febbc8e3c4cad4ea1783f139178fbb4888e1f089a9ed6cd3efd/langbase-0.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "27a3e0e0faed11be69990066dc932bc49bf3875bed7f1aa2ee2bcdb193cdd5f3",
"md5": "d56c8d109f4f46e6af4901d513288d98",
"sha256": "494524c4c8caa71a95bef4ca4eff928330c6112438e27c8d34b194028693f238"
},
"downloads": -1,
"filename": "langbase-0.0.3.tar.gz",
"has_sig": false,
"md5_digest": "d56c8d109f4f46e6af4901d513288d98",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 37532,
"upload_time": "2025-08-07T00:37:19",
"upload_time_iso_8601": "2025-08-07T00:37:19.052459Z",
"url": "https://files.pythonhosted.org/packages/27/a3/e0e0faed11be69990066dc932bc49bf3875bed7f1aa2ee2bcdb193cdd5f3/langbase-0.0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-07 00:37:19",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "LangbaseInc",
"github_project": "langbase-python-sdk",
"github_not_found": true,
"lcname": "langbase"
}
JSON
