Working with LangDB Client

You can connect to LangDB AI Gateway using python client library.

1

Install LangDB Python Client

To install pylangdb

pip install pylangdb
2

Initialize LangDb Client

from pylangdb import LangDb
client = LangDb(
    api_key="your_api_key", 
    project_id="your_project_id"
)
3

Make your first completions request

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Say hello!"}
]

response = client.completion(
    model="gemini-1.5-pro-latest",
    messages=messages,
    temperature=0.7,
    max_tokens=100
)
4

Get Messages

thread_id = response["thread_id"]
messages = client.get_messages(thread_id)

# Access message details
for message in messages:
    print(f"Type: {message.type}")
    print(f"Content: {message.content}")
    if message.tool_calls:
        for tool_call in message.tool_calls:
            print(f"Tool: {tool_call.function.name}")
5

Get Usage

usage = client.get_usage(thread_id)
6

Get Analytics

You can get analytics of your LLM calls.

# Get raw analytics data
analytics = client.get_analytics(
    tags="tag1,tag2",
    start_time_us=None,  # Optional: defaults to 24 hours ago
    end_time_us=None     # Optional: defaults to current time
)

# Get analytics as a pandas DataFrame
df = client.get_analytics_dataframe(
    tags="tag1,tag2",
    start_time_us=None,
    end_time_us=None
)
Updated on