Replies: 1 comment
-
Hi, @carpric. I'm Dosu, and I'm helping the LlamaIndex team manage their backlog. I wanted to let you know that we are marking this issue as stale. Based on my understanding, the issue you reported is related to the missing inclusion of sources (documents consulted) in the response when using OpenAIAgent and QueryPlanTool with multiple nodes that have dependencies. Currently, there hasn't been any activity or updates on this issue. If this issue is still relevant to the latest version of the LlamaIndex repository, please let the LlamaIndex team know by commenting on this issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days. Thank you for your contribution, and please don't hesitate to reach out if you have any further questions or concerns. |
Beta Was this translation helpful? Give feedback.
-
Question Validation
Question
Hello everyone,
I've seen using OpenAIAgent and QueryPlanTool for my use-case and works really good. However, when the QueryPlan is composed of multiple nodes that includes dependencies, the sources (i.e. documents consulted and such) is not included as for instance if only one node is executed.
Example:
Calling function: query_tool with args: {
"nodes": [
{
"id": 1,
"query_str": "Question A",
"tool_name": "test",
"dependencies": []
},
{
"id": 2,
"query_str": "Question B",
"tool_name": "test",
"dependencies": []
},
{
"id": 3,
"query_str": "Qyestion C",
"tool_name": "test",
"dependencies": [1, 2]
}
]
}
The response.sources (documents consulted/metadata) don't include any information after this query is executed. Anyone knows how I can solve this problem?
Note: When only one node is executed (no dependencies), I can extract the documents consulted.
Thank you in advance.
Beta Was this translation helpful? Give feedback.
All reactions