Gerard Conway 2

Hi, I've downloaded the circular bar chart mod. I've configured it using data from the 'Introduction to Spotfire' example dxp. See my config below. I cannot get beyond the config error, 'Cannot read properties of undefined (reading 'data')' Am I doing something wrong? Thanks, Gerard

Thanks @Marcelo Gallardo for the input. Minimal query payload will be useful for testing. However, using the attached .env file. My Orchestrator container just cycles quickly between running and restarting and continues to do that. I have attached the container log. Am I doing something wrong in my .env. Orchestrator Container Restarting.txt

My Orchestrator is up and running. I can run the root endpoint and it returns, {"message": "DSML LLM Orchestrator - REST API"} I've reviewed the OrchestratorRequest Schema in the Swagger API documentation but it's still not clear which parameters are required and which are optional. When the inputs are (String | null) is null an acceptable value. I'm doubtful of that for parameters like index_name. Is retriever_type required? What are valid values? What is the appropriate value for a setup a milvus vector database with only spotfire docs loaded? For llm_mode what is the best default, 'chat' or 'completions'? Here is my current query (request body payload) { "request_tag": "MyOrchRequest", "temperature": 0, "index_name": "spotfiredocs", "index_score_threshold": 0, "index_topk": 5, "llm_name": "gpt-3.5-turbo-1106", "llm_mode": "completions", "system_prompt": "Your are an AI assistant. Answer the question based on the context below. Keep the answer short and concise.", "user_intent": "QueryIntent", "history": null, "client_data": null, "prompt": "How to create a bar chart?" } It results in a error, KeyError: 'QueryIntent', see attached container log. If I set user_intent to null, the error changes to KeyError: 'SpotfireHelp'. Finally, if I try and use the Spotfire Copilot panel in Spotfire Analyst e.g. 'Ask Sample HowTo Question', I get the following single line error in the container log POST / HTTP/1.1" 405 Method Not Allowed Orchestrator Container Error QueryIntent.txt Orchestrator Container Error SpotfireHelp.txt

It is not at all clear what are the minimal set of required parameters that must be set to get a working Orchestrator container. The parameter list has greatly increased since the previous copilot release. Do the LANGCHAIN_... parameters need to be present and do they need to be set to legitimate values or can they be left blank? Same question for the .._PLUGIN_.. parameters? I have included them with dummy values and my container at least appears to start. Also the Architecture Diagram in the Getting Started Guide does not show anything related to LANGCHAIN or PLUGINS. I assume these are there to extend the functionality rather than run the default setup. VECTOR_DB_TOKEN is also a new parameter. I believe it's typically username:password combined for Milvus. How is this handled if authentication hasn't been enabled on Milvus, will the VECTOR_DB_TOKEN value be ignored? I'm using Milvus as the Vector Database and have successfully load the Spotfire docs. I've attached the attached the.env file I'm using for the Orchestrator which starts ok and is running. I want to run a test query against the orchestrator REST endpoint. However, I unsure of the parameter values required to execute a test query against the Vector Database. Which parameters are required and which might be optional. what should the index_name be? the collection name in Milvus i.e. spotfiredocs? retriever type? llm_name? is this the model name to use e.g. gpt-3.5-turbo-1106? llm_mode? I guess this is the new mode feature and should be 'Spotfire' for my test. Assuming I have loaded only the enclosed Spotfiredocs what the most basic request body needed to run a test query. Thanks, Gerard Orchestrator Container Error.txt

Thank you @Marcelo Gallardo I will wait for the updated release

Hi I'm trying to setup Copilot, using Melvus as my vector db and OpenAI as my LLM provider. I have successfully used the data loader container to load and index the Spotfire docs. I can search the docs using the Data Loader APIs. However, when I start the Orchestrator container I'm unable to call the '/orchestartor/' end point using the simple prompt 'How to create a bar chart?'. (screenshot attached) I get the follow error message, full log attached. error_message='Unknown request URL: POST /v1/openai/deployments/gpt-35-turbo/chat/completions?api-version=2023-03-15-preview. It's strange because I have not set the OPENAI_API_KEY environment variable nor have I used that parameter in the yaml compose file. .env and .yml files attached. It seems like the Orchestartor is adding the api-version parameter by default. Does the OpenAI API even take an api-version parameter. It seems to be more associated with Azure OpenAI. Any guidance appreciated. Thanks, Gerard .env docker-compose-orchestrator.yml Orchestrator Container Error.txt

Hi Charlie, If you are working with PerkinElmer's Lead Discovery product then there are a series of Chemical Functions available which can be used as part of Calculated Columns. Insert -> Calcualted Column, and you will see the Chemical Functions category, there is Convert function that allows you to convert to multiple chemical formats, for instance SMILES notation to be generated and exported: Chemical function: Convert(Arg1, Arg2) Convert Arg1 molecule to the MimeType of Arg2. Below MimeTypes can be defined in Arg2: - CDX - CDXML - Molfile - SMILES Example: Convert([structure], "SMILES"). This will produce a new SMILES column in your Data Table. You can then use standard export features to export the SMILES. Hope that helps, Gerard

Here's something similar using Statistics Server and R. Passes in a text column and returns a wordcloud image to display in a text area and a data table containing the word frequencies.