底层结构化数据提取

from llama_index.core.program.function_program import get_function_tool

tool = get_function_tool(Invoice)

resp = llm.chat_with_tools(
    [tool],
    # chat_history=chat_history,  # can optionally pass in chat history instead of user_msg
    user_msg="Extract an invoice from the following text: " + text,
    tool_required=True,  # can optionally force the tool call
)

tool_calls = llm.get_tool_calls_from_response(
    resp, error_on_no_tool_calls=False
)

outputs = []
for tool_call in tool_calls:
    if tool_call.tool_name == "Invoice":
        outputs.append(Invoice(**tool_call.tool_kwargs))

# use your outputs
print(outputs[0])

from llama_index.core.program.function_program import get_function_tool

tool = get_function_tool(LineItem)

resp = llm.chat_with_tools(
    [tool],
    user_msg="Extract line items from the following text: " + text,
    allow_parallel_tool_calls=True,
)

tool_calls = llm.get_tool_calls_from_response(
    resp, error_on_no_tool_calls=False
)

outputs = []
for tool_call in tool_calls:
    if tool_call.tool_name == "LineItem":
        outputs.append(LineItem(**tool_call.tool_kwargs))

# use your outputs
print(outputs)

schema = Invoice.model_json_schema()
prompt = "Here is a JSON schema for an invoice: " + json.dumps(
    schema, indent=2
)
prompt += (
    """
  Extract an invoice from the following text.
  Format your output as a JSON object according to the schema above.
  Do not include any other text than the JSON object.
  Omit any markdown formatting. Do not include any preamble or explanation.
"""
    + text
)

response = llm.complete(prompt)

print(response)

invoice = Invoice.model_validate_json(response.text)

pprint(invoice)