Avala + LangChain

pip install avala langchain langchain-openai

from avala import Client
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate

client = Client()  # reads AVALA_API_KEY
llm = ChatOpenAI(model="gpt-4o")

# Fetch dataset metadata
datasets = client.datasets.list()
dataset_info = [
    {"name": d.name, "uid": d.uid, "items": d.item_count}
    for d in datasets
]

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a data management assistant. Help the user understand their annotation datasets."),
    ("user", "Here are my datasets:\n{datasets}\n\nWhich dataset should I prioritize for labeling and why?"),
])

chain = prompt | llm
response = chain.invoke({"datasets": dataset_info})
print(response.content)

import json
import time
from avala import Client
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate

client = Client()
llm = ChatOpenAI(model="gpt-4o-mini")

# Export and download
export = client.exports.create(project="proj_abc123")
while export.status != "completed":
    time.sleep(2)
    export = client.exports.get(export.uid)

import requests
annotations = requests.get(export.download_url).json()

# Classify each annotation's complexity
prompt = ChatPromptTemplate.from_messages([
    ("system", "Classify the annotation complexity as 'simple', 'moderate', or 'complex' based on the number and type of objects."),
    ("user", "Annotations: {annotations}\n\nReturn only the classification word."),
])

chain = prompt | llm

for ann in annotations[:10]:  # Sample
    result = chain.invoke({"annotations": json.dumps(ann.get("annotations", []))})
    ann["complexity"] = result.content.strip().lower()
    print(f"{ann['file_name']}: {ann['complexity']}")

from avala import Client
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate

client = Client()
llm = ChatOpenAI(model="gpt-4o")

# Fetch project and task stats
projects = list(client.projects.list())
project_summaries = []

for project in projects:
    tasks = list(client.tasks.list(project=project.uid))
    status_counts = {}
    for task in tasks:
        status = task.status or "unknown"
        status_counts[status] = status_counts.get(status, 0) + 1

    project_summaries.append({
        "name": project.name,
        "status": project.status,
        "tasks": status_counts,
    })

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a project analytics assistant. Answer questions about annotation project progress."),
    ("user", "Project data:\n{projects}\n\nQuestion: {question}"),
])

chain = prompt | llm

# Ask questions
questions = [
    "Which project has the most pending tasks?",
    "What's the overall completion rate across all projects?",
    "Which projects might need more annotators?",
]

for q in questions:
    answer = chain.invoke({"projects": project_summaries, "question": q})
    print(f"Q: {q}\nA: {answer.content}\n")

# With Claude Desktop, Cursor, or VS Code — the MCP server
# exposes tools like list_datasets, get_project, create_export
# that AI assistants can call directly.