From 153836ff899c31e3fe548d2f3de23919fb317284 Mon Sep 17 00:00:00 2001
From: dylan1218 <dylan1218@live.com>
Date: Wed, 28 Feb 2024 12:00:14 -0500
Subject: [PATCH] JSON path prompt debug facilitation (#9097)
---
.../core/indices/struct_store/json_query.py | 26 +++++++++++++++++++
.../core/prompts/default_prompts.py | 8 +++++-
2 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/llama-index-core/llama_index/core/indices/struct_store/json_query.py b/llama-index-core/llama_index/core/indices/struct_store/json_query.py
index 4a76dcf513..8d8bee667d 100644
--- a/llama-index-core/llama_index/core/indices/struct_store/json_query.py
+++ b/llama-index-core/llama_index/core/indices/struct_store/json_query.py
@@ -1,5 +1,6 @@
import json
import logging
+import re
from typing import Any, Callable, Dict, List, Optional, Union
from llama_index.core.base.base_query_engine import BaseQueryEngine
@@ -43,6 +44,19 @@ DEFAULT_RESPONSE_SYNTHESIS_PROMPT = PromptTemplate(
)
+def default_output_response_parser(llm_output: str) -> str:
+ """Attempts to parse the JSON path prompt output. Only applicable if the default prompt is used."""
+ try:
+ llm_output_parsed = re.search(
+ pattern=r"JSONPath:\s+(.*)", string=llm_output
+ ).groups()[0]
+ except Exception as exc:
+ raise ValueError(
+ f"JSON Path could not be parsed in the LLM response after the 'JSONPath' identifier. Try passing a custom JSON path prompt and processor."
+ ) from exc
+ return llm_output_parsed
+
+
def default_output_processor(llm_output: str, json_value: JSONType) -> JSONType:
"""Default output processor that extracts values based on JSON Path expressions."""
# Split the given string into separate JSON Path expressions
@@ -164,6 +178,12 @@ class JSONQueryEngine(BaseQueryEngine):
**self._output_kwargs,
)
+ # removes JSONPath: prefix from returned JSON path prompt call
+ if self._json_path_prompt == DEFAULT_JSON_PATH_PROMPT:
+ json_path_response_str = default_output_response_parser(
+ json_path_response_str
+ )
+
if self._verbose:
print_text(f"> JSONPath Output: {json_path_output}\n")
@@ -193,6 +213,12 @@ class JSONQueryEngine(BaseQueryEngine):
query_str=query_bundle.query_str,
)
+ # removes JSONPath: prefix from returned JSON path prompt call
+ if self._json_path_prompt == DEFAULT_JSON_PATH_PROMPT:
+ json_path_response_str = default_output_response_parser(
+ json_path_response_str
+ )
+
if self._verbose:
print_text(
f"> JSONPath Instructions:\n" f"```\n{json_path_response_str}\n```\n"
diff --git a/llama-index-core/llama_index/core/prompts/default_prompts.py b/llama-index-core/llama_index/core/prompts/default_prompts.py
index 997ec53165..3049970893 100644
--- a/llama-index-core/llama_index/core/prompts/default_prompts.py
+++ b/llama-index-core/llama_index/core/prompts/default_prompts.py
@@ -390,8 +390,14 @@ DEFAULT_JSON_PATH_TMPL = (
"{schema}\n"
"Given a task, respond with a JSON Path query that "
"can retrieve data from a JSON value that matches the schema.\n"
+ "Provide the JSON Path query in the following format: 'JSONPath: <JSONPath>'\n"
+ "You must include the value 'JSONPath:' before the provided JSON Path query."
+ "Example Format:\n"
+ "Task: What is John's age?\n"
+ "Response: JSONPath: $.John.age\n"
+ "Let's try this now: \n\n"
"Task: {query_str}\n"
- "JSONPath: "
+ "Response: "
)
DEFAULT_JSON_PATH_PROMPT = PromptTemplate(
--
GitLab