From c49a5e162071053b83f9050ed4ace0149e201da3 Mon Sep 17 00:00:00 2001
From: Huu Le <39040748+leehuwuj@users.noreply.github.com>
Date: Wed, 14 Aug 2024 14:39:14 +0700
Subject: [PATCH] chore: update wrong env name, add error handling for next
question (#232)
---
.changeset/kind-beans-sit.md | 5 ++
.changeset/ten-worms-pump.md | 5 ++
helpers/env-variables.ts | 2 +-
helpers/providers/azure.ts | 8 +--
.../typescript/streaming/suggestion.ts | 4 +-
.../components/settings/python/settings.py | 2 +-
.../fastapi/app/api/services/suggestion.py | 55 ++++++++++++-------
7 files changed, 52 insertions(+), 29 deletions(-)
create mode 100644 .changeset/kind-beans-sit.md
create mode 100644 .changeset/ten-worms-pump.md
diff --git a/.changeset/kind-beans-sit.md b/.changeset/kind-beans-sit.md
new file mode 100644
index 00000000..05c562ec
--- /dev/null
+++ b/.changeset/kind-beans-sit.md
@@ -0,0 +1,5 @@
+---
+"create-llama": patch
+---
+
+Add error handling for generating the next question
diff --git a/.changeset/ten-worms-pump.md b/.changeset/ten-worms-pump.md
new file mode 100644
index 00000000..c2c64711
--- /dev/null
+++ b/.changeset/ten-worms-pump.md
@@ -0,0 +1,5 @@
+---
+"create-llama": patch
+---
+
+Fix wrong api key variable in Azure OpenAI provider
diff --git a/helpers/env-variables.ts b/helpers/env-variables.ts
index e3f041ce..1ddd269c 100644
--- a/helpers/env-variables.ts
+++ b/helpers/env-variables.ts
@@ -311,7 +311,7 @@ const getModelEnvs = (modelConfig: ModelConfig): EnvVar[] => {
...(modelConfig.provider === "azure-openai"
? [
{
- name: "AZURE_OPENAI_KEY",
+ name: "AZURE_OPENAI_API_KEY",
description: "The Azure OpenAI key to use.",
value: modelConfig.apiKey,
},
diff --git a/helpers/providers/azure.ts b/helpers/providers/azure.ts
index 74f90142..e450715f 100644
--- a/helpers/providers/azure.ts
+++ b/helpers/providers/azure.ts
@@ -9,6 +9,7 @@ const ALL_AZURE_OPENAI_CHAT_MODELS: Record<string, { openAIModel: string }> = {
openAIModel: "gpt-3.5-turbo-16k",
},
"gpt-4o": { openAIModel: "gpt-4o" },
+ "gpt-4o-mini": { openAIModel: "gpt-4o-mini" },
"gpt-4": { openAIModel: "gpt-4" },
"gpt-4-32k": { openAIModel: "gpt-4-32k" },
"gpt-4-turbo": {
@@ -26,6 +27,9 @@ const ALL_AZURE_OPENAI_CHAT_MODELS: Record<string, { openAIModel: string }> = {
"gpt-4o-2024-05-13": {
openAIModel: "gpt-4o-2024-05-13",
},
+ "gpt-4o-mini-2024-07-18": {
+ openAIModel: "gpt-4o-mini-2024-07-18",
+ },
};
const ALL_AZURE_OPENAI_EMBEDDING_MODELS: Record<
@@ -35,10 +39,6 @@ const ALL_AZURE_OPENAI_EMBEDDING_MODELS: Record<
openAIModel: string;
}
> = {
- "text-embedding-ada-002": {
- dimensions: 1536,
- openAIModel: "text-embedding-ada-002",
- },
"text-embedding-3-small": {
dimensions: 1536,
openAIModel: "text-embedding-3-small",
diff --git a/templates/components/llamaindex/typescript/streaming/suggestion.ts b/templates/components/llamaindex/typescript/streaming/suggestion.ts
index 83567111..0dacaead 100644
--- a/templates/components/llamaindex/typescript/streaming/suggestion.ts
+++ b/templates/components/llamaindex/typescript/streaming/suggestion.ts
@@ -33,8 +33,8 @@ export async function generateNextQuestions(
const questions = extractQuestions(response.text);
return questions;
} catch (error) {
- console.error("Error: ", error);
- throw error;
+ console.error("Error when generating the next questions: ", error);
+ return [];
}
}
diff --git a/templates/components/settings/python/settings.py b/templates/components/settings/python/settings.py
index b723bf3e..bb828705 100644
--- a/templates/components/settings/python/settings.py
+++ b/templates/components/settings/python/settings.py
@@ -82,7 +82,7 @@ def init_azure_openai():
dimensions = os.getenv("EMBEDDING_DIM")
azure_config = {
- "api_key": os.environ["AZURE_OPENAI_KEY"],
+ "api_key": os.environ["AZURE_OPENAI_API_KEY"],
"azure_endpoint": os.environ["AZURE_OPENAI_ENDPOINT"],
"api_version": os.getenv("AZURE_OPENAI_API_VERSION")
or os.getenv("OPENAI_API_VERSION"),
diff --git a/templates/types/streaming/fastapi/app/api/services/suggestion.py b/templates/types/streaming/fastapi/app/api/services/suggestion.py
index 406b0aec..ea563b17 100644
--- a/templates/types/streaming/fastapi/app/api/services/suggestion.py
+++ b/templates/types/streaming/fastapi/app/api/services/suggestion.py
@@ -1,3 +1,4 @@
+import logging
from typing import List
from app.api.routers.models import Message
@@ -9,11 +10,14 @@ NEXT_QUESTIONS_SUGGESTION_PROMPT = PromptTemplate(
"You're a helpful assistant! Your task is to suggest the next question that user might ask. "
"\nHere is the conversation history"
"\n---------------------\n{conversation}\n---------------------"
- "Given the conversation history, please give me $number_of_questions questions that you might ask next!"
+ "Given the conversation history, please give me {number_of_questions} questions that you might ask next!"
)
N_QUESTION_TO_GENERATE = 3
+logger = logging.getLogger("uvicorn")
+
+
class NextQuestions(BaseModel):
"""A list of questions that user might ask next"""
@@ -21,28 +25,37 @@ class NextQuestions(BaseModel):
class NextQuestionSuggestion:
+
@staticmethod
async def suggest_next_questions(
messages: List[Message],
number_of_questions: int = N_QUESTION_TO_GENERATE,
) -> List[str]:
- # Reduce the cost by only using the last two messages
- last_user_message = None
- last_assistant_message = None
- for message in reversed(messages):
- if message.role == "user":
- last_user_message = f"User: {message.content}"
- elif message.role == "assistant":
- last_assistant_message = f"Assistant: {message.content}"
- if last_user_message and last_assistant_message:
- break
- conversation: str = f"{last_user_message}\n{last_assistant_message}"
-
- output: NextQuestions = await Settings.llm.astructured_predict(
- NextQuestions,
- prompt=NEXT_QUESTIONS_SUGGESTION_PROMPT,
- conversation=conversation,
- nun_questions=number_of_questions,
- )
-
- return output.questions
+ """
+ Suggest the next questions that user might ask based on the conversation history
+ Return as empty list if there is an error
+ """
+ try:
+ # Reduce the cost by only using the last two messages
+ last_user_message = None
+ last_assistant_message = None
+ for message in reversed(messages):
+ if message.role == "user":
+ last_user_message = f"User: {message.content}"
+ elif message.role == "assistant":
+ last_assistant_message = f"Assistant: {message.content}"
+ if last_user_message and last_assistant_message:
+ break
+ conversation: str = f"{last_user_message}\n{last_assistant_message}"
+
+ output: NextQuestions = await Settings.llm.astructured_predict(
+ NextQuestions,
+ prompt=NEXT_QUESTIONS_SUGGESTION_PROMPT,
+ conversation=conversation,
+ number_of_questions=number_of_questions,
+ )
+
+ return output.questions
+ except Exception as e:
+ logger.error(f"Error when generating next question: {e}")
+ return []
--
GitLab