Issues with the responses received from Azure OpenAI using my own data.
Hello everyone! I have a flow that makes a request to the Azure OpenAI API, and I am using fetch for this request. However, it doesn't always return the responses I expect. For example, there are certain questions that it only responds to in the Azure OpenAI portal, but not in the request from Buildship.
On other occasions, it responds in English despite setting in the system prompt that its responses should be in Spanish.
I'm using cURL with parameters such as "data_source" and their nested objects.
{
"data_sources": [
{
"type": "azure_search",
"parameters": {
"endpoint": "search_endpoint",
"index_name": "search_index",
"semantic_configuration": "index-semantic-configuration",
"query_type": "vectorSemanticHybrid",
"in_scope": true,
"role_information": "You are a helpful assistant",
"filter": null,
"strictness": 3,
"top_n_documents": 6,
"authentication": {
"type": "api_key",
"key": "search_key"
},
"embedding_dependency": {
"type": "deployment_name",
"deployment_name": "text-embedding-3-small"
}
}
}
],
"messages": [
{
"role": "system",
"content": "You are a helpful assistant"
},
{
"role": "user",
"content": "prompt"
}
],
"deployment": "model",
"temperature": 0,
"top_p": 1,
"max_tokens": 800,
"stop": null
//stream: true, -> I disabled this option because I can't receive information in real-time; however, I don't think that it affects the issue.
}
Has anyone had this problem and managed to solve it? I appreciate your responses.
On other occasions, it responds in English despite setting in the system prompt that its responses should be in Spanish.
I'm using cURL with parameters such as "data_source" and their nested objects.
{
"data_sources": [
{
"type": "azure_search",
"parameters": {
"endpoint": "search_endpoint",
"index_name": "search_index",
"semantic_configuration": "index-semantic-configuration",
"query_type": "vectorSemanticHybrid",
"in_scope": true,
"role_information": "You are a helpful assistant",
"filter": null,
"strictness": 3,
"top_n_documents": 6,
"authentication": {
"type": "api_key",
"key": "search_key"
},
"embedding_dependency": {
"type": "deployment_name",
"deployment_name": "text-embedding-3-small"
}
}
}
],
"messages": [
{
"role": "system",
"content": "You are a helpful assistant"
},
{
"role": "user",
"content": "prompt"
}
],
"deployment": "model",
"temperature": 0,
"top_p": 1,
"max_tokens": 800,
"stop": null
//stream: true, -> I disabled this option because I can't receive information in real-time; however, I don't think that it affects the issue.
}
Has anyone had this problem and managed to solve it? I appreciate your responses.
