Default to gpt-4o-mini as online chat model

This commit is contained in:
Debanjum Singh Solanky 2024-09-10 18:43:54 -07:00
parent ae74c6ca55
commit 179357b28a
3 changed files with 4 additions and 4 deletions

View file

@ -206,7 +206,7 @@ Using Ollama? See the [Ollama Integration](/advanced/ollama) section for more cu
::: :::
1. Go to the [OpenAI settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/) in the server admin settings to add an OpenAI processor conversation config. This is where you set your API key and server API base URL. The API base URL is optional - it's only relevant if you're using another OpenAI-compatible proxy server. 1. Go to the [OpenAI settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/) in the server admin settings to add an OpenAI processor conversation config. This is where you set your API key and server API base URL. The API base URL is optional - it's only relevant if you're using another OpenAI-compatible proxy server.
2. Go over to configure your [chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/). Set the `chat-model` field to a supported chat model[^1] of your choice. For example, you can specify `gpt-4-turbo-preview` if you're using OpenAI. 2. Go over to configure your [chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/). Set the `chat-model` field to a supported chat model[^1] of your choice. For example, you can specify `gpt-4o` if you're using OpenAI.
- Make sure to set the `model-type` field to `OpenAI`. - Make sure to set the `model-type` field to `OpenAI`.
- The `tokenizer` and `max-prompt-size` fields are optional. Set them only if you're sure of the tokenizer or token limit for the model you're using. Contact us if you're unsure what to do here. - The `tokenizer` and `max-prompt-size` fields are optional. Set them only if you're sure of the tokenizer or token limit for the model you're using. Contact us if you're unsure what to do here.

View file

@ -23,7 +23,7 @@ logger = logging.getLogger(__name__)
def extract_questions( def extract_questions(
text, text,
model: Optional[str] = "gpt-4-turbo-preview", model: Optional[str] = "gpt-4o-mini",
conversation_log={}, conversation_log={},
api_key=None, api_key=None,
api_base_url=None, api_base_url=None,
@ -43,7 +43,7 @@ def extract_questions(
[ [
f'Q: {chat["intent"]["query"]}\nKhoj: {{"queries": {chat["intent"].get("inferred-queries") or list([chat["intent"]["query"]])}}}\nA: {chat["message"]}\n\n' f'Q: {chat["intent"]["query"]}\nKhoj: {{"queries": {chat["intent"].get("inferred-queries") or list([chat["intent"]["query"]])}}}\nA: {chat["message"]}\n\n'
for chat in conversation_log.get("chat", [])[-4:] for chat in conversation_log.get("chat", [])[-4:]
if chat["by"] == "khoj" and "text-to-image" not in chat["intent"].get("type") if chat["by"] == "khoj" and "to-image" not in chat["intent"].get("type")
] ]
) )

View file

@ -9,7 +9,7 @@ app_env_filepath = "~/.khoj/env"
telemetry_server = "https://khoj.beta.haletic.com/v1/telemetry" telemetry_server = "https://khoj.beta.haletic.com/v1/telemetry"
content_directory = "~/.khoj/content/" content_directory = "~/.khoj/content/"
default_offline_chat_model = "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF" default_offline_chat_model = "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF"
default_online_chat_model = "gpt-4-turbo-preview" default_online_chat_model = "gpt-4o-mini"
empty_config = { empty_config = {
"search-type": { "search-type": {