gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: Support structured output parsed from OpenAI

Browse source 
Added support for structured output (JSON mode) from the OpenAI API in `openai.py` and `azure_openai.py`.

When `response_format` is used to request structured data, the new logic checks for the `message.parsed` attribute. If it exists, it's serialized into a JSON string as the final content. If not, the code falls back to the existing `message.content` handling, ensuring backward compatibility.
This commit is contained in:
yangdx 2025-11-21 12:46:31 +08:00
parent c9e1c86e81
commit 9f69c5bf85
2 changed files with 57 additions and 37 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
lightrag/llm/azure_openai.py
View file

@ -113,9 +113,20 @@ async def azure_openai_complete_if_cache(
return inner() return inner()
else: else:
content = response.choices[0].message.content message = response.choices[0].message
if r"\u" in content:
content = safe_unicode_decode(content.encode("utf-8")) # Handle parsed responses (structured output via response_format)
# When using beta.chat.completions.parse(), the response is in message.parsed
if hasattr(message, "parsed") and message.parsed is not None:
# Serialize the parsed structured response to JSON
content = message.parsed.model_dump_json()
logger.debug("Using parsed structured response from API")
else:
# Handle regular content responses
content = message.content
if content and r"\u" in content:
content = safe_unicode_decode(content.encode("utf-8"))
return content return content

77
lightrag/llm/openai.py
View file

@ -453,46 +453,55 @@ async def openai_complete_if_cache(
raise InvalidResponseError("Invalid response from OpenAI API") raise InvalidResponseError("Invalid response from OpenAI API")
message = response.choices[0].message message = response.choices[0].message
content = getattr(message, "content", None)
reasoning_content = getattr(message, "reasoning_content", "") # Handle parsed responses (structured output via response_format)
# When using beta.chat.completions.parse(), the response is in message.parsed
if hasattr(message, "parsed") and message.parsed is not None:
# Serialize the parsed structured response to JSON
final_content = message.parsed.model_dump_json()
logger.debug("Using parsed structured response from API")
else:
# Handle regular content responses
content = getattr(message, "content", None)
reasoning_content = getattr(message, "reasoning_content", "")
# Handle COT logic for non-streaming responses (only if enabled) # Handle COT logic for non-streaming responses (only if enabled)
final_content = "" final_content = ""
if enable_cot: if enable_cot:
# Check if we should include reasoning content # Check if we should include reasoning content
should_include_reasoning = False should_include_reasoning = False
if reasoning_content and reasoning_content.strip(): if reasoning_content and reasoning_content.strip():
if not content or content.strip() == "": if not content or content.strip() == "":
# Case 1: Only reasoning content, should include COT # Case 1: Only reasoning content, should include COT
should_include_reasoning = True should_include_reasoning = True
final_content = ( final_content = (
content or "" content or ""
) # Use empty string if content is None ) # Use empty string if content is None
else:
# Case 3: Both content and reasoning_content present, ignore reasoning
should_include_reasoning = False
final_content = content
else: else:
# Case 3: Both content and reasoning_content present, ignore reasoning # No reasoning content, use regular content
should_include_reasoning = False final_content = content or ""
final_content = content
# Apply COT wrapping if needed
if should_include_reasoning:
if r"\u" in reasoning_content:
reasoning_content = safe_unicode_decode(
reasoning_content.encode("utf-8")
)
final_content = f"<think>{reasoning_content}</think>{final_content}"
else: else:
# No reasoning content, use regular content # COT disabled, only use regular content
final_content = content or "" final_content = content or ""
# Apply COT wrapping if needed # Validate final content
if should_include_reasoning: if not final_content or final_content.strip() == "":
if r"\u" in reasoning_content: logger.error("Received empty content from OpenAI API")
reasoning_content = safe_unicode_decode( await openai_async_client.close() # Ensure client is closed
reasoning_content.encode("utf-8") raise InvalidResponseError("Received empty content from OpenAI API")
)
final_content = f"<think>{reasoning_content}</think>{final_content}"
else:
# COT disabled, only use regular content
final_content = content or ""
# Validate final content
if not final_content or final_content.strip() == "":
logger.error("Received empty content from OpenAI API")
await openai_async_client.close() # Ensure client is closed
raise InvalidResponseError("Received empty content from OpenAI API")
# Apply Unicode decoding to final content if needed # Apply Unicode decoding to final content if needed
if r"\u" in final_content: if r"\u" in final_content: