diff --git a/llama-index-core/llama_index/core/command_line/mappings.json b/llama-index-core/llama_index/core/command_line/mappings.json
index 15d6126eff904df07afab3b326a518c46a13f010..378f8498e5d6c5f2dd9a59dd6fb3c97d2e756342 100644
--- a/llama-index-core/llama_index/core/command_line/mappings.json
+++ b/llama-index-core/llama_index/core/command_line/mappings.json
@@ -906,5 +906,6 @@
"run_jobs": "llama_index.core.async_utils",
"DecomposeQueryTransform": "llama_index.core.query.query_transform.base",
"get_eval_results": "llama_index.core.evaluation.eval_utils",
- "REPLICATE_MULTI_MODAL_LLM_MODELS": "llama_index.multi_modal_llms.replicate.base"
+ "REPLICATE_MULTI_MODAL_LLM_MODELS": "llama_index.multi_modal_llms.replicate.base",
+ "QueryUnderstandingPack": "llama_index.packs.query_understanding_agent"
}
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/.gitignore b/llama-index-packs/llama-index-packs-query-understanding-agent/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..990c18de229088f55c6c514fd0f2d49981d1b0e7
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/.gitignore
@@ -0,0 +1,153 @@
+llama_index/_static
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+bin/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+etc/
+include/
+lib/
+lib64/
+parts/
+sdist/
+share/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+.ruff_cache
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+notebooks/
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pyvenv.cfg
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Jetbrains
+.idea
+modules/
+*.swp
+
+# VsCode
+.vscode
+
+# pipenv
+Pipfile
+Pipfile.lock
+
+# pyright
+pyrightconfig.json
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/BUILD b/llama-index-packs/llama-index-packs-query-understanding-agent/BUILD
new file mode 100644
index 0000000000000000000000000000000000000000..2d3d88d1eab9ce4898e7dfc34d7224ae0467316c
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/BUILD
@@ -0,0 +1,7 @@
+poetry_requirements(
+ name="poetry",
+)
+
+python_requirements(
+ name="reqs",
+)
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/Makefile b/llama-index-packs/llama-index-packs-query-understanding-agent/Makefile
new file mode 100644
index 0000000000000000000000000000000000000000..b9eab05aa370629a4a3de75df3ff64cd53887b68
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/Makefile
@@ -0,0 +1,17 @@
+GIT_ROOT ?= $(shell git rev-parse --show-toplevel)
+
+help: ## Show all Makefile targets.
+ @grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[33m%-30s\033[0m %s\n", $$1, $$2}'
+
+format: ## Run code autoformatters (black).
+ pre-commit install
+ git ls-files | xargs pre-commit run black --files
+
+lint: ## Run linters: pre-commit (black, ruff, codespell) and mypy
+ pre-commit install && git ls-files | xargs pre-commit run --show-diff-on-failure --files
+
+test: ## Run tests via pytest.
+ pytest tests
+
+watch-docs: ## Build and watch documentation.
+ sphinx-autobuild docs/ docs/_build/html --open-browser --watch $(GIT_ROOT)/llama_index/
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/README.md b/llama-index-packs/llama-index-packs-query-understanding-agent/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2fcadd1c28969ac005c66ff98cd70393cce40aee
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/README.md
@@ -0,0 +1,39 @@
+# LlamaIndex Packs Integration: Query Understanding Agent
+
+This LlamaPack implements Query Understanding Agent
+
+Taking inspiration from Humans - when asked a query, humans would clarify what the query means before proceeding if the human sensed the query is unclear. This LlamaPack implements this.
+
+### Installation
+
+```bash
+pip install llama-index
+```
+
+## CLI Usage
+
+You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
+
+```bash
+llamaindex-cli download-llamapack QueryUnderstandingAgent --download-dir ./query_understanding_agent
+```
+
+You can then inspect the files at `./query_understanding_agent` and use them as a template for your own project.
+
+## Code Usage
+
+You can download the pack to a the `./query_understanding_agent` directory:
+
+```python
+from llama_index.core.llama_pack import download_llama_pack
+
+# download and install dependencies
+QueryUnderstandingAgentPack = download_llama_pack(
+ "QueryUnderstandingAgent", "./query_understanding_agent"
+)
+
+# You can use any llama-hub loader to get documents!
+```
+
+From here, you can use the pack, or inspect and modify the pack in `./query_understanding_agent`.
+See example notebook for usage.
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/examples/query_understanding_agent.ipynb b/llama-index-packs/llama-index-packs-query-understanding-agent/examples/query_understanding_agent.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..8dea220651eb5c4e006df14b07ff5ac434fcc0e3
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/examples/query_understanding_agent.ipynb
@@ -0,0 +1,288 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": null,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from dotenv import load_dotenv\n",
+ "\n",
+ "load_dotenv()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Grab Data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "--2024-03-07 21:54:37-- https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt\n",
+ "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 2606:50c0:8000::154, 2606:50c0:8001::154, 2606:50c0:8002::154, ...\n",
+ "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|2606:50c0:8000::154|:443... connected.\n",
+ "HTTP request sent, awaiting response... 200 OK\n",
+ "Length: 75042 (73K) [text/plain]\n",
+ "Saving to: ‘data/paul_graham/paul_graham_essay.txt’\n",
+ "\n",
+ "data/paul_graham/pa 100%[===================>] 73.28K --.-KB/s in 0.01s \n",
+ "\n",
+ "2024-03-07 21:54:37 (5.91 MB/s) - ‘data/paul_graham/paul_graham_essay.txt’ saved [75042/75042]\n",
+ "\n"
+ ]
+ }
+ ],
+ "source": [
+ "!mkdir -p 'data/paul_graham/'\n",
+ "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "steve_jobs_text = \"\"\"1995 was the year when Steve Jobs was approaching the end of his exile from Apple after being kicked out of the company a decade earlier. Him as his new company, NeXT, were brought back in to save Apple from near bankruptcy.Jul 25, 2018\"\"\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Load Data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from llama_index.core import SimpleDirectoryReader, VectorStoreIndex\n",
+ "from llama_index.core.response.pprint_utils import pprint_response\n",
+ "from llama_index.llms.openai import OpenAI\n",
+ "from llama_index.core.schema import Document\n",
+ "\n",
+ "# Tool 1\n",
+ "llm = OpenAI()\n",
+ "data = SimpleDirectoryReader(input_dir=\"./data/paul_graham/\").load_data()\n",
+ "index = VectorStoreIndex.from_documents(data)\n",
+ "\n",
+ "# Tool 2\n",
+ "steve_index = VectorStoreIndex.from_documents([Document(text=steve_jobs_text)])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Agents"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from llama_index.core.agent import AgentRunner\n",
+ "from llama_index.packs.query_understanding_agent.step import (\n",
+ " QueryUnderstandingAgentWorker,\n",
+ " HumanInputRequiredException,\n",
+ ")\n",
+ "from llama_index.core.tools import QueryEngineTool\n",
+ "\n",
+ "llm = OpenAI(model=\"gpt-4\")\n",
+ "\n",
+ "tools = [\n",
+ " QueryEngineTool.from_defaults(\n",
+ " query_engine=index.as_query_engine(),\n",
+ " description=\"A tool that is useful for retrieving specific snippets from the Paul Graham's life\",\n",
+ " ),\n",
+ " QueryEngineTool.from_defaults(\n",
+ " query_engine=steve_index.as_query_engine(),\n",
+ " description=\"A tool that is useful for retrieving specific snippets from the Steve Jobs's life\",\n",
+ " ),\n",
+ "]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Baseline"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This does not programmatically pause to detect ambiguity to allow user to provide input. Not only that, sometimes this hallucinate to a random subject."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1;3;38;5;200mThought: The user is asking about the author but hasn't specified which author. I have tools to query information about Paul Graham and Steve Jobs. I need to ask the user to specify the author.\n",
+ "\n",
+ "Action: None\n",
+ "Answer: Could you please specify which author you are referring to? I have information about Paul Graham and Steve Jobs.\n",
+ "\u001b[0m"
+ ]
+ }
+ ],
+ "source": [
+ "from llama_index.core.agent import ReActAgentWorker\n",
+ "\n",
+ "callback_manager = llm.callback_manager\n",
+ "agent_worker = ReActAgentWorker.from_tools(\n",
+ " tools,\n",
+ " llm=llm,\n",
+ " verbose=True,\n",
+ " callback_manager=callback_manager,\n",
+ ")\n",
+ "agent = AgentRunner(agent_worker, callback_manager=callback_manager)\n",
+ "orig_question = \"What did the author do in the summer of 1995?\"\n",
+ "response = agent.chat(orig_question)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Query Understanding Agent Worker"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "This allows the agent to ask user for clarification if the user query is unclear"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# from llama_index.core.agent import ReActAgentWorker\n",
+ "callback_manager = llm.callback_manager\n",
+ "agent_worker = QueryUnderstandingAgentWorker.from_tools(\n",
+ " tools,\n",
+ " llm=llm,\n",
+ " callback_manager=callback_manager,\n",
+ ")\n",
+ "agent = AgentRunner(agent_worker, callback_manager=callback_manager)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "response: In the summer of 1995, Steve Jobs was involved in the process of returning to Apple after his departure from the company a decade earlier.\n"
+ ]
+ }
+ ],
+ "source": [
+ "# from llama_index.llms.openai import OpenAI\n",
+ "\n",
+ "orig_question = \"what did he do in the summer of 1995?\"\n",
+ "llm = OpenAI(model=\"gpt-4\")\n",
+ "clarifying_questions = []\n",
+ "\n",
+ "try:\n",
+ " response = agent.chat(orig_question)\n",
+ "except HumanInputRequiredException as e:\n",
+ " response = input(e.message)\n",
+ " clarifying_questions.append((e.message, response))\n",
+ " should_end = False\n",
+ " while not should_end:\n",
+ " clarifying_texts = \"\\n\".join(\n",
+ " [\n",
+ " f\"\"\"\n",
+ " Q: {question}\n",
+ " A: {answer}\n",
+ " \"\"\"\n",
+ " for question, answer in clarifying_questions\n",
+ " ]\n",
+ " )\n",
+ " query_text = f\"\"\"\n",
+ "Given a query and a set of clarifying questions, please rewrite the query to be more clear.\n",
+ "Example:\n",
+ "Q: What trajectory is the monthly earning from the three months: April, May and June?\n",
+ "Clarifying Questions:\n",
+ " Q: What year are you referring to?\n",
+ " A: In 2022\n",
+ " Q: What company are you referring to?\n",
+ " A: Uber\n",
+ "Rewrite: What was the trajectory of Uber's monthly earnings for the months of April, May, and June in 2022?\n",
+ "\n",
+ "Q:{orig_question}\n",
+ "Clarifying Questions: {clarifying_texts}\n",
+ "Rewrite: \"\"\"\n",
+ " rewrite_response = llm.complete(query_text)\n",
+ " orig_question = rewrite_response\n",
+ " try:\n",
+ " output = agent.chat(rewrite_response.text)\n",
+ " should_end = True\n",
+ " print(f\"response: {output.response}\")\n",
+ " except HumanInputRequiredException as er:\n",
+ " response = input(er.message)\n",
+ " clarifying_questions.append((er.message, response))"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/BUILD b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/BUILD
new file mode 100644
index 0000000000000000000000000000000000000000..db46e8d6c978c67e301dd6c47bee08c1b3fd141c
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/BUILD
@@ -0,0 +1 @@
+python_sources()
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/__init__.py b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..ef02cda6e15c5823e1bbb8b80f1225da3ae45f26
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/__init__.py
@@ -0,0 +1,4 @@
+from llama_index.packs.query_understanding_agent.base import QueryUnderstandingAgentPack
+
+
+__all__ = ["QueryUnderstandingAgentPack"]
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/base.py b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/base.py
new file mode 100644
index 0000000000000000000000000000000000000000..698c1b77519bb2bba1ac31e0bc2fd7891fb1061a
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/base.py
@@ -0,0 +1,58 @@
+"""Query Understanding agent pack."""
+
+from typing import Any, Dict, List, Optional
+
+from llama_index.core.agent import AgentRunner
+from llama_index.core.callbacks import CallbackManager
+from llama_index.core.llama_pack.base import BaseLlamaPack
+from llama_index.core.llms.llm import LLM
+from llama_index.core.tools.types import BaseTool
+from llama_index.llms.openai import OpenAI
+
+from .step import QueryUnderstandingAgentWorker
+
+
+class QueryUnderstandingAgentPack(BaseLlamaPack):
+ """LLMCompilerAgent pack.
+
+ Args:
+ tools (List[BaseTool]): List of tools to use.
+ llm (Optional[LLM]): LLM to use.
+ """
+
+ def __init__(
+ self,
+ tools: List[BaseTool],
+ llm: Optional[LLM] = None,
+ callback_manager: Optional[CallbackManager] = None,
+ agent_worker_kwargs: Optional[Dict[str, Any]] = None,
+ agent_runner_kwargs: Optional[Dict[str, Any]] = None,
+ ) -> None:
+ """Init params."""
+ self.llm = llm or OpenAI(model="gpt-4")
+ self.callback_manager = callback_manager or self.llm.callback_manager
+ self.agent_worker = QueryUnderstandingAgentWorker.from_tools(
+ tools,
+ llm=llm,
+ verbose=True,
+ callback_manager=self.callback_manager,
+ **(agent_worker_kwargs or {})
+ )
+ self.agent = AgentRunner(
+ self.agent_worker,
+ callback_manager=self.callback_manager,
+ **(agent_runner_kwargs or {})
+ )
+
+ def get_modules(self) -> Dict[str, Any]:
+ """Get modules."""
+ return {
+ "llm": self.llm,
+ "callback_manager": self.callback_manager,
+ "agent_worker": self.agent_worker,
+ "agent": self.agent,
+ }
+
+ def run(self, *args: Any, **kwargs: Any) -> Any:
+ """Run the pipeline."""
+ return self.agent.chat(*args, **kwargs)
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/step.py b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/step.py
new file mode 100644
index 0000000000000000000000000000000000000000..38ef228566c7181d69ad39b232a1f7386fecc049
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/llama_index/packs/query_understanding_agent/step.py
@@ -0,0 +1,277 @@
+from llama_index.core.bridge.pydantic import Field, BaseModel, PrivateAttr
+from llama_index.core import PromptTemplate
+from typing import Any, Dict, List, Optional
+from dataclasses import dataclass, field
+
+import uuid
+
+from llama_index.core.agent.types import (
+ Task,
+ TaskStep,
+ TaskStepOutput,
+)
+from llama_index.core.agent.custom.simple import CustomSimpleAgentWorker
+from llama_index.core.callbacks import (
+ trace_method,
+)
+from llama_index.core.chat_engine.types import AgentChatResponse
+
+
+from llama_index.core.agent import CustomSimpleAgentWorker, Task
+from typing import Dict, Any, List, Tuple, Optional
+from llama_index.core.tools import BaseTool, QueryEngineTool
+from llama_index.core.query_engine import RouterQueryEngine
+from llama_index.core.prompts import ChatPromptTemplate
+
+from llama_index.core.llms import ChatMessage, MessageRole
+
+DEFAULT_PROMPT_STR = """
+Given the question, the tools provided and response, please determine if the question is clear enough to provide the response (with the help of the tools).
+If the question is not clear enough, provide a clarifying_question for user to clarify. Provide a clarifying question that only need plan text answers. DO NOT ASK the user a similar question to the one the user asks you.
+If the response is sufficient, then return has_error: false, and requires_human_input: false. No need to make the response perfect, as long as it is sufficient.
+
+Given the questions and tools, here are several ways to clarify questions:
+- If there are multiple tools for each timeframe, then if the timeframe is not specified in the question, we need to ask to be clear on the timeframe.
+- Be clear on which subjects the user is referring to, ask which subject the user is referring to if there are a tool for each subject
+
+Example 1:
+Tools:
+A useful tool for financial documents for uber in 2022
+A useful tool for financial documents for lyft in 2022
+
+Question: What is the company's financial stats in 2022?
+Response: Uber's financial stats is 20k in the year 2022
+
+Answer:
+{{"requires_human_input": true, "has_error": true, "clarifying_question": "Which company are you referring to?", "explanation": "Given the tools and the question, it is not clear which company the user is referring to"}}
+
+Example 2:
+Tools:
+A useful tool for financial documents for uber in 2022
+A useful tool for financial documents for lyft in 2022
+
+Question: What is the Uber's financial stats in 2022?
+Response: Uber's financial stats is 20k in the year 2022
+
+Answer:
+{{"requires_human_input": false, "has_error": false, "clarifying_question": "", "explanation": "It is quite clear that the user is referring to uber and the year 2022"}}
+
+Tools:
+{tools}
+
+Question: {query_str}
+Response: {response_str}
+
+Please return the evaluation of the response in the following JSON format.
+Answer:
+"""
+
+
+@dataclass
+class AgentChatComplexResponse(AgentChatResponse):
+ """Agent chat response with metadata."""
+
+ output: Dict[str, Any] = field(default_factory=dict)
+
+
+def get_chat_prompt_template(
+ system_prompt: str, current_reasoning: Tuple[str, str]
+) -> ChatPromptTemplate:
+ system_msg = ChatMessage(role=MessageRole.SYSTEM, content=system_prompt)
+ messages = [system_msg]
+ for raw_msg in current_reasoning:
+ if raw_msg[0] == "user":
+ messages.append(ChatMessage(role=MessageRole.USER, content=raw_msg[1]))
+ else:
+ messages.append(ChatMessage(role=MessageRole.ASSISTANT, content=raw_msg[1]))
+ return ChatPromptTemplate(message_templates=messages)
+
+
+class ResponseEval(BaseModel):
+ """Evaluation of whether the response has an error."""
+
+ clarifying_question: str = Field(
+ ..., description="The clarifying question, if human input is required"
+ )
+ explanation: str = Field(
+ ...,
+ description=(
+ "The explanation for the error OR for the clarifying question."
+ "Can include the direct stack trace as well."
+ ),
+ )
+ has_error: bool = Field(..., description="Whether the response has an error")
+ requires_human_input: bool = Field(
+ ...,
+ description="Whether the response needs human input. If true, the clarifying question should be provided.",
+ )
+
+
+class HumanInputRequiredException(Exception):
+ """Exception raised when human input is required."""
+
+ def __init__(
+ self,
+ message="Human input is required",
+ task_id: Optional[str] = None,
+ step: TaskStep = None,
+ ):
+ self.message = message
+ self.task_id = task_id
+ self.step = step
+ super().__init__(self.message)
+
+
+class QueryUnderstandingAgentWorker(CustomSimpleAgentWorker):
+ """Agent worker that adds a retry layer on top of a router.
+
+ Continues iterating until there's no errors / task is done.
+
+ """
+
+ prompt_str: str = Field(default=DEFAULT_PROMPT_STR)
+ max_iterations: int = Field(default=10)
+
+ _router_query_engine: RouterQueryEngine = PrivateAttr()
+
+ def __init__(self, tools: List[BaseTool], **kwargs: Any) -> None:
+ """Init params."""
+ # validate that all tools are query engine tools
+ for tool in tools:
+ if not isinstance(tool, QueryEngineTool):
+ raise ValueError(
+ f"Tool {tool.metadata.name} is not a query engine tool."
+ )
+ self._router_query_engine = RouterQueryEngine.from_defaults(
+ llm=kwargs.get("llm"),
+ select_multi=False,
+ query_engine_tools=tools,
+ verbose=kwargs.get("verbose", False),
+ )
+ super().__init__(
+ tools=tools,
+ **kwargs,
+ )
+
+ def _initialize_state(self, task: Task, **kwargs: Any) -> Dict[str, Any]:
+ """Initialize state."""
+ return {"count": 0, "current_reasoning": []}
+
+ def _run_llm_program(self, query_str, response_str, tools):
+ for _ in range(3):
+ try:
+ return self.llm.structured_predict(
+ ResponseEval,
+ PromptTemplate(self.prompt_str),
+ query_str=query_str,
+ response_str=str(response_str),
+ tools=tools,
+ )
+ except Exception as e:
+ print(f"Attempt failed with error: {e}")
+ continue
+ raise Exception("Failed to run LLM program after 3 attempts")
+
+ def _run_step(
+ self, state: Dict[str, Any], task: Task, input: Optional[str] = None
+ ) -> Tuple[AgentChatComplexResponse, bool]:
+ """Run step.
+
+ Returns:
+ Tuple of (agent_response, is_done)
+
+ """
+ if input is not None:
+ # if input is specified, override input
+ new_input = input
+ elif "new_input" not in state:
+ new_input = task.input
+ else:
+ new_input = state["new_input"]["text"]
+
+ if self.verbose:
+ print(f"> Current Input: {new_input}")
+
+ # first run router query engine
+ response = self._router_query_engine.query(new_input)
+
+ # append to current reasoning
+ state["current_reasoning"].extend(
+ [("user", new_input), ("assistant", str(response))]
+ )
+
+ # Then, check for errors
+ # dynamically create pydantic program for structured output extraction based on template
+ tools = "\n".join([a.description for a in self._router_query_engine._metadatas])
+ response_eval = self._run_llm_program(
+ query_str=new_input, response_str=str(response), tools=tools
+ )
+
+ if self.verbose:
+ print(f"> Question: {new_input}")
+ print(f"> Response: {response}")
+ print(f"> Response eval: {response_eval.dict()}")
+
+ # return response
+ if response_eval.requires_human_input:
+ return (
+ AgentChatComplexResponse(
+ response=response,
+ output={
+ "type": "requires_human_input",
+ "clarifying_question": str(response_eval.clarifying_question),
+ "has_error": response_eval.has_error,
+ "explanation": response_eval.explanation,
+ },
+ ),
+ True,
+ )
+
+ return AgentChatComplexResponse(response=response), not response_eval.has_error
+
+ @trace_method("run_step")
+ def run_step(self, step: TaskStep, task: Task, **kwargs: Any) -> TaskStepOutput:
+ """Run step."""
+ output, is_done = self._run_step(step.step_state, task, input=step.input)
+ if output.output and output.output["type"] == "requires_human_input":
+ raise HumanInputRequiredException(
+ message=output.output["clarifying_question"],
+ task_id=task.task_id,
+ step=step,
+ )
+
+ response = self._get_task_step_response(output, step, is_done)
+ # sync step state with task state
+ task.extra_state.update(step.step_state)
+ return response
+
+ def _get_task_step_response(
+ self,
+ output: Dict,
+ step: TaskStep,
+ is_done: bool,
+ ) -> TaskStepOutput:
+ """Get task step response."""
+ if is_done:
+ new_steps = []
+ else:
+ new_steps = [
+ step.get_next_step(
+ step_id=str(uuid.uuid4()),
+ # NOTE: input is unused
+ input=None,
+ )
+ ]
+
+ return TaskStepOutput(
+ output=output,
+ task_step=step,
+ is_last=is_done,
+ next_steps=new_steps,
+ )
+
+ def _finalize_task(self, state: Dict[str, Any], **kwargs) -> None:
+ """Finalize task."""
+ # nothing to finalize here
+ # this is usually if you want to modify any sort of
+ # internal state beyond what is set in `_initialize_state`
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/pyproject.toml b/llama-index-packs/llama-index-packs-query-understanding-agent/pyproject.toml
new file mode 100644
index 0000000000000000000000000000000000000000..55dd33421244e1c7db4f5664ea3a24bd24483903
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/pyproject.toml
@@ -0,0 +1,58 @@
+[build-system]
+build-backend = "poetry.core.masonry.api"
+requires = ["poetry-core"]
+
+[tool.codespell]
+check-filenames = true
+check-hidden = true
+# Feel free to un-skip examples, and experimental, you will just need to
+# work through many typos (--write-changes and --interactive will help)
+skip = "*.csv,*.html,*.json,*.jsonl,*.pdf,*.txt,*.ipynb"
+
+[tool.llamahub]
+contains_example = false
+import_path = "llama_index.packs.query_understanding_agent"
+
+[tool.llamahub.class_authors]
+QueryUnderstandingPack = "llama-index"
+
+[tool.mypy]
+disallow_untyped_defs = true
+# Remove venv skip when integrated with pre-commit
+exclude = ["_static", "build", "examples", "notebooks", "venv"]
+ignore_missing_imports = true
+python_version = "3.8"
+
+[tool.poetry]
+authors = ["Sasha Sheng <hackgoofer@gmail.com>"]
+description = "llama-index packs query understanding agent integration"
+exclude = ["**/BUILD"]
+license = "MIT"
+name = "llama-index-packs-query-understanding-agent"
+packages = [{include = "llama_index/"}]
+readme = "README.md"
+version = "0.1.0"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+llama-index-core = "^0.10.0"
+llama-index-llms-openai = "^0.1.7"
+
+[tool.poetry.group.dev.dependencies]
+black = {extras = ["jupyter"], version = "<=23.9.1,>=23.7.0"}
+codespell = {extras = ["toml"], version = ">=v2.2.6"}
+ipython = "8.10.0"
+jupyter = "^1.0.0"
+mypy = "0.991"
+pre-commit = "3.2.0"
+pylint = "2.15.10"
+pytest = "7.2.1"
+pytest-mock = "3.11.1"
+ruff = "0.0.292"
+tree-sitter-languages = "^1.8.0"
+types-Deprecated = ">=0.1.0"
+types-PyYAML = "^6.0.12.12"
+types-protobuf = "^4.24.0.4"
+types-redis = "4.5.5.0"
+types-requests = "2.28.11.8" # TODO: unpin when mypy>0.991
+types-setuptools = "67.1.0.0"
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/requirements.txt b/llama-index-packs/llama-index-packs-query-understanding-agent/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/tests/BUILD b/llama-index-packs/llama-index-packs-query-understanding-agent/tests/BUILD
new file mode 100644
index 0000000000000000000000000000000000000000..dabf212d7e7162849c24a733909ac4f645d75a31
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/tests/BUILD
@@ -0,0 +1 @@
+python_tests()
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/tests/__init__.py b/llama-index-packs/llama-index-packs-query-understanding-agent/tests/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/llama-index-packs/llama-index-packs-query-understanding-agent/tests/test_packs_query_understanding_agent.py b/llama-index-packs/llama-index-packs-query-understanding-agent/tests/test_packs_query_understanding_agent.py
new file mode 100644
index 0000000000000000000000000000000000000000..9329d52faf49350d6acd251f05b4a0d791be8838
--- /dev/null
+++ b/llama-index-packs/llama-index-packs-query-understanding-agent/tests/test_packs_query_understanding_agent.py
@@ -0,0 +1,7 @@
+from llama_index.core.llama_pack import BaseLlamaPack
+from llama_index.packs.query_understanding_agent import QueryUnderstandingAgentPack
+
+
+def test_class():
+ names_of_base_classes = [b.__name__ for b in QueryUnderstandingAgentPack.__mro__]
+ assert BaseLlamaPack.__name__ in names_of_base_classes