_construct_responses_api_input() — langchain Function Reference
Architecture documentation for the _construct_responses_api_input() function in base.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD b988bc7d_ceff_06f1_193c_a22abc7a149f["_construct_responses_api_input()"] 2b046911_ea21_8e2e_ba0d_9d03da8d7bda["base.py"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|defined in| 2b046911_ea21_8e2e_ba0d_9d03da8d7bda a129387a_a0b1_9985_0b43_bfc1f161529a["_construct_responses_api_payload()"] a129387a_a0b1_9985_0b43_bfc1f161529a -->|calls| b988bc7d_ceff_06f1_193c_a22abc7a149f fd643003_13df_3a67_6bdc_07576981e414["_convert_message_to_dict()"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|calls| fd643003_13df_3a67_6bdc_07576981e414 83f2962a_a930_da72_3b90_e0aa308605d3["_make_computer_call_output_from_message()"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|calls| 83f2962a_a930_da72_3b90_e0aa308605d3 19a91a7c_09b7_1e12_cab8_29322483cdfd["_make_custom_tool_output_from_message()"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|calls| 19a91a7c_09b7_1e12_cab8_29322483cdfd b1594e89_965d_0f6c_e9b0_511a58b3e737["_ensure_valid_tool_message_content()"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|calls| b1594e89_965d_0f6c_e9b0_511a58b3e737 00006c95_8bb4_f0a5_7955_81d9e07c009d["_format_annotation_from_lc()"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|calls| 00006c95_8bb4_f0a5_7955_81d9e07c009d ad1a549b_b34e_2769_401e_132731113e67["_pop_index_and_sub_index()"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|calls| ad1a549b_b34e_2769_401e_132731113e67 57d40c25_4875_99e8_1bae_5dd1aad3c2b3["_convert_chat_completions_blocks_to_responses()"] b988bc7d_ceff_06f1_193c_a22abc7a149f -->|calls| 57d40c25_4875_99e8_1bae_5dd1aad3c2b3 style b988bc7d_ceff_06f1_193c_a22abc7a149f fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/partners/openai/langchain_openai/chat_models/base.py lines 4106–4273
def _construct_responses_api_input(messages: Sequence[BaseMessage]) -> list:
"""Construct the input for the OpenAI Responses API."""
input_ = []
for lc_msg in messages:
if isinstance(lc_msg, AIMessage):
lc_msg = _convert_from_v03_ai_message(lc_msg)
msg = _convert_message_to_dict(lc_msg, api="responses")
if isinstance(msg.get("content"), list) and all(
isinstance(block, dict) for block in msg["content"]
):
tcs: list[types.ToolCall] = [
{
"type": "tool_call",
"name": tool_call["name"],
"args": tool_call["args"],
"id": tool_call.get("id"),
}
for tool_call in lc_msg.tool_calls
]
msg["content"] = _convert_from_v1_to_responses(msg["content"], tcs)
else:
msg = _convert_message_to_dict(lc_msg, api="responses")
# Get content from non-standard content blocks
if isinstance(msg["content"], list):
for i, block in enumerate(msg["content"]):
if isinstance(block, dict) and block.get("type") == "non_standard":
msg["content"][i] = block["value"]
# "name" parameter unsupported
if "name" in msg:
msg.pop("name")
if msg["role"] == "tool":
tool_output = msg["content"]
computer_call_output = _make_computer_call_output_from_message(
cast(ToolMessage, lc_msg)
)
custom_tool_output = _make_custom_tool_output_from_message(lc_msg) # type: ignore[arg-type]
if computer_call_output:
input_.append(computer_call_output)
elif custom_tool_output:
input_.append(custom_tool_output)
else:
tool_output = _ensure_valid_tool_message_content(tool_output)
function_call_output = {
"type": "function_call_output",
"output": tool_output,
"call_id": msg["tool_call_id"],
}
input_.append(function_call_output)
elif msg["role"] == "assistant":
if isinstance(msg.get("content"), list):
for block in msg["content"]:
if isinstance(block, dict) and (block_type := block.get("type")):
# Aggregate content blocks for a single message
if block_type in ("text", "output_text", "refusal"):
msg_id = block.get("id")
if block_type in ("text", "output_text"):
# Defensive check: block may not have "text" key
text = block.get("text")
if text is None:
# Skip blocks without text content
continue
new_block = {
"type": "output_text",
"text": text,
"annotations": [
_format_annotation_from_lc(annotation)
for annotation in block.get("annotations") or []
],
}
elif block_type == "refusal":
new_block = {
"type": "refusal",
"refusal": block["refusal"],
}
for item in input_:
if (item_id := item.get("id")) and item_id == msg_id:
# If existing block with this ID, append to it
if "content" not in item:
item["content"] = []
item["content"].append(new_block)
breakDomain
Subdomains
Calls
Called By
Source
Frequently Asked Questions
What does _construct_responses_api_input() do?
_construct_responses_api_input() is a function in the langchain codebase, defined in libs/partners/openai/langchain_openai/chat_models/base.py.
Where is _construct_responses_api_input() defined?
_construct_responses_api_input() is defined in libs/partners/openai/langchain_openai/chat_models/base.py at line 4106.
What does _construct_responses_api_input() call?
_construct_responses_api_input() calls 7 function(s): _convert_chat_completions_blocks_to_responses, _convert_message_to_dict, _ensure_valid_tool_message_content, _format_annotation_from_lc, _make_computer_call_output_from_message, _make_custom_tool_output_from_message, _pop_index_and_sub_index.
What calls _construct_responses_api_input()?
_construct_responses_api_input() is called by 1 function(s): _construct_responses_api_payload.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free