Getting HTTP 400 errors on /api/embeddings about lumos HOT 7 CLOSED

@vicendominguez do you see any errors in the console for the Chrome extension's background script? Based on the server code, it looks like one of the validation steps is failing. Validation:

1. request body is set
2. model is set
3. model is valid
4. working directory is set
5. embedding option is enabled

from lumos.

@andrewnguonly i found the problem.

TLDR

You need (must) to have llama2 model installed: ollama pull llama2.

CONTEXT

llama2 model was not installed in my ollama serve because my default LLM is mistral.

I was trying to play with this line but the Llama2 model appears to be more integrated within the LangChain node module.

from lumos.

I'll update the README to specify that llama2 is required because of the hardcoded model. Will also include instructions to change the model.

from lumos.

Not for me @andrewnguonly .....

diff --git a/src/scripts/background.ts b/src/scripts/background.ts
index 4d69d32..15cfb7b 100644
--- a/src/scripts/background.ts
+++ b/src/scripts/background.ts
@@ -9,7 +9,7 @@ import { formatDocumentsAsString } from "langchain/util/document";


 const OLLAMA_BASE_URL = "http://localhost:11434";
-const OLLAMA_MODEL = "llama2";
+const OLLAMA_MODEL = "mistral";
 var context = "";

 chrome.runtime.onMessage.addListener(async function (request) {

Rebuilt, reloaded and inspected from your plugin (network tab). This is the request payload:

{"prompt":"texttextext","model":"llama2"}

That model llama2 has a bad smell....

Two questions:

• Could the npm build cache anything i don't know? (nodejs is out of my scope sorry)
• Could you try it again but making a ollama rm llama2 in your environment?

PS: i've updated nodejs to the last versions just in case.

from lumos.

I was trying to play with this line but the Llama2 model appears to be more integrated within the LangChain node module.

@vicendominguez, I was able to run the extension w/ mistral after downloading the model and changing the hardcoded model value. Were you seeing some other error?

from lumos.

@vicendominguez

Could the npm build cache anything i don't know? (nodejs is out of my scope sorry)

I don't think so, but try deleting the entire /dist folder and then rerun npm run build to rebuild all the source files.

Could you try it again but making a ollama rm llama2 in your environment?

I tried this and the extension was able to call the API w/ the mistral model. To clarify, I tried w/ both llama2 and mistral downloaded and with only mistral downloaded.

from lumos.

@vicendominguez, please reopen this issue if you're still unable to get the extension to call the Ollama API w/ the desired model. Thanks.

from lumos.