import os
import openai
os.environ['OPENAI_API_KEY'] = "sk-***"
openai.api_key = os.environ["OPENAI_API_KEY"]
from llama_index import Document, SummaryIndex, VectorStoreIndex, SimpleDirectoryReader
from llama_index.tools import QueryEngineTool, ToolMetadata
from llama_index.query_engine import SubQuestionQueryEngine
from llama_index.callbacks import CallbackManager, LlamaDebugHandler
from llama_index import ServiceContext
from llama_index.question_gen.llm_generators import LLMQuestionGenerator
from qdrant_client import QdrantClient
from llama_index.vector_stores.qdrant import QdrantVectorStore
# Using the LlamaDebugHandler to print the trace of the sub questions
# captured by the SUB_QUESTION callback event type
llama_debug = LlamaDebugHandler(print_trace_on_end=True)
callback_manager = CallbackManager([llama_debug])
service_context = ServiceContext.from_defaults(
callback_manager=callback_manager
)
vector_index = VectorStoreIndex.from_documents(
documents=[
Document(text="whe have the color green for trees")
],
service_context=service_context
)
vector_query_engine = vector_index.as_query_engine()
# setup base query engine as tool
query_engine_tools = [
QueryEngineTool(
query_engine=vector_query_engine,
metadata=ToolMetadata(
name="tree_colors",
description="Everything around trees",
),
),
]
query_engine = SubQuestionQueryEngine.from_defaults(
query_engine_tools=query_engine_tools,
service_context=service_context,
question_gen=LLMQuestionGenerator.from_defaults(
service_context=service_context
)
)
response = query_engine.query(
"What is the color for trees?"
)
print(response)
return msgTraceback (most recent call last):
File "/python3.11/site-packages/pydantic/v1/main.py", line 522, in parse_obj
obj = dict(obj)
^^^^^^^^^
ValueError: dictionary update sequence element #0 has length 1; 2 is required
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "<string>", line 130, in <module>
File "<string>", line 116, in python_function
File "/python3.11/site-packages/llama_index/core/base_query_engine.py", line 40, in query
return self._query(str_or_query_bundle)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/python3.11/site-packages/llama_index/query_engine/sub_question_query_engine.py", line 129, in _query
sub_questions = self._question_gen.generate(self._metadatas, query_bundle)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/python3.11/site-packages/llama_index/question_gen/llm_generators.py", line 78, in generate
parse = self._prompt.output_parser.parse(prediction)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/python3.11/site-packages/llama_index/question_gen/output_parser.py", line 15, in parse
sub_questions = [SubQuestion.parse_obj(item) for item in json_dict]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/python3.11/site-packages/llama_index/question_gen/output_parser.py", line 15, in <listcomp>
sub_questions = [SubQuestion.parse_obj(item) for item in json_dict]
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/python3.11/site-packages/pydantic/v1/main.py", line 525, in parse_obj
raise ValidationError([ErrorWrapper(exc, loc=ROOT_KEY)], cls) from e
pydantic.v1.error_wrappers.ValidationError: 1 validation error for SubQuestion
__root__
SubQuestion expected dict not str (type=type_error)OpenAIQuestionGenerator since it uses the function calling apifinal_engine_no_metadata = SubQuestionQueryEngine.from_defaults(
query_engine_tools=[
QueryEngineTool(
query_engine=engine_no_metadata,
metadata=ToolMetadata(
name="sec_filing_documents",
description="financial information on companies",
),
)
],
question_gen=question_gen,
use_async=True,
)LLMQuestonGenerator, use OpenAIQuestionGeneratorfrom llama_index.question_gen.llm_generators import OpenAIQuestionGenerator, DEFAULT_OPENAI_SUB_QUESTION_PROMPT_TMPL
service_context = ServiceContext.from_defaults(
llm=llm, text_splitter=text_splitter
)
question_gen = OpenAIQuestionGenerator.from_defaults(
llm=service_context.llm,
prompt_template_str="""
Follow the example, but instead of giving a question, always prefix the question
with: 'By first identifying and quoting the most relevant sources, '.
"""
+ DEFAULT_OPENAI_SUB_QUESTION_PROMPT_TMPL,
)ImportError Traceback (most recent call last)
<ipython-input-14-24df7212ac1e> in <cell line: 16>()
14 # )
15
---> 16 from llama_index.question_gen.llm_generators import OpenAIQuestionGenerator, DEFAULT_OPENAI_SUB_QUESTION_PROMPT_TMPL
17
18 service_context = ServiceContext.from_defaults(
ImportError: cannot import name 'OpenAIQuestionGenerator' from 'llama_index.question_gen.llm_generators' (/usr/local/lib/python3.10/dist-packages/llama_index/question_gen/llm_generators.py)
---------------------------------------------------------------------------
NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.
To view examples of installing some common dependencies, click the
"Open Examples" button below.from llama_index.question_gen.openai_generator import OpenAIQuestionGenerator, DEFAULT_OPENAI_SUB_QUESTION_PROMPT_TMPL
OpenAIQuestionGenerator improved the performance.response_no_metadata with LLMQuestionGenerator from the original notebook:Generated 4 sub questions.
[sec_filing_documents] Q: What was the cost due to research and development for Uber in 2019
[sec_filing_documents] Q: What was the cost due to sales and marketing for Uber in 2019
[sec_filing_documents] Q: What was the cost due to research and development for Lyft in 2019
[sec_filing_documents] Q: What was the cost due to sales and marketing for Lyft in 2019
[sec_filing_documents] A: The cost due to sales and marketing for Uber in 2019 was $814,122 in thousands.
[sec_filing_documents] A: The cost due to research and development for Uber in 2019 was $1,505,640 in thousands.
[sec_filing_documents] A: The cost of research and development for Lyft in 2019 was $1,505,640 in thousands.
[sec_filing_documents] A: The cost due to sales and marketing for Lyft in 2019 was $814,122 in thousands.
{
"Uber": {
"Research and Development": 1505.64,
"Sales and Marketing": 814.122
},
"Lyft": {
"Research and Development": 1505.64,
"Sales and Marketing": 814.122
}
}response_no_metadata with OpenAIQuestionGenerator:Generated 4 sub questions.
[sec_filing_documents] Q: By first identifying and quoting the most relevant sources, what was the cost due to research and development for Uber in 2019 in millions of USD?
[sec_filing_documents] Q: By first identifying and quoting the most relevant sources, what was the cost due to sales and marketing for Uber in 2019 in millions of USD?
[sec_filing_documents] Q: By first identifying and quoting the most relevant sources, what was the cost due to research and development for Lyft in 2019 in millions of USD?
[sec_filing_documents] Q: By first identifying and quoting the most relevant sources, what was the cost due to sales and marketing for Lyft in 2019 in millions of USD?
[sec_filing_documents] A: The cost due to sales and marketing for Lyft in 2019 was $4,626 million.
[sec_filing_documents] A: The cost due to sales and marketing for Uber in 2019 was $4,626 million.
[sec_filing_documents] A: The cost due to research and development for Uber in 2019 was $4,836 million.
[sec_filing_documents] A: The cost due to research and development for Lyft in 2019 was $1,505,640 in thousands of USD, which is equivalent to $1,505.64 million.
{
"Uber": {
"Research and Development": 4836,
"Sales and Marketing": 4626
},
"Lyft": {
"Research and Development": 1505.64,
"Sales and Marketing": 4626
}
}