Documentation Index
Fetch the complete documentation index at: https://futureagi.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Integrating Prompt Templates into Spans
By instrumenting the prompt template, users can fully utilize Future AGI’s prompt playground. There’s no need to deploy a new template version to test if changes in prompt text or variables achieve the desired effect. Instead, you can experiment with these modifications directly in the playground UI.
Implementation Details
We provide a using_prompt_template context manager to add a prompt template into the current OpenTelemetry Context. FI auto-instrumentors will read this Context and pass the prompt template fields as span attributes, adhering to the traceAI semantic conventions.
Required Parameters
| Parameter | Type | Description | Example |
|---|
| template | str | The string for the prompt template | ”Please describe the weather forecast for on “ |
| version | str | Identifier for the template version | ”v1.0” |
| variables | Dict[str] | Dictionary containing variables to fill the template | {"city": "San Francisco", "date": "March 27"} |
Sample Implementation
Begin by installing the necessary dependencies:
pip install fi-instrumentation-otel traceai_openai openai
import os
from fi_instrumentation import register, Transport, using_attributes
from traceai_openai import OpenAIInstrumentor
from fi_instrumentation.fi_types import ProjectType
from traceai_langchain import LangChainInstrumentor
from fi_instrumentation import register
from fi_instrumentation.fi_types import (
ProjectType,
)
from traceai_langchain import LangChainInstrumentor
os.environ["GOOGLE_API_KEY"] = "google_api_key"
print(os.environ.get("GOOGLE_API_KEY"))
os.environ["OPENAI_API_KEY"] = "futureagi_openai_api_key"
os.environ["FI_API_KEY"] = "futureagi_api_key"
os.environ["FI_SECRET_KEY"] = "futureagi_secret_key"
# Setup OTel via our register function
trace_provider = register(
project_type=ProjectType.OBSERVE,
project_name="<project_name>", # Your project name
transport=Transport.HTTP, # Transport mechanism for your traces
)
OpenAIInstrumentor().instrument(tracer_provider=trace_provider)
LangChainInstrumentor().instrument(tracer_provider=trace_provider)
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
with using_attributes(
prompt_template="<prompt_template_name>",
prompt_template_label="<prompt_template_label>",
):
prompt = ChatPromptTemplate.from_template("{x} {y} {z}?").partial(x="why is", z="blue")
chain = prompt | ChatOpenAI(model_name="gpt-3.5-turbo")
result = chain.invoke({"y": "sky"})
print(f"Response: {result}")
