Naoki Nakamichi

Hi team, I have a client who is planning to implement Spotfire Copilot. Are there any system requirements for the Data Loader and Orchestrator? It would be helpful if you could provide both minimum and recommended specifications. Thanks, Naoki Nakamichi

@tsubasa takayama In my case, I made a very simple mistake. While it appeared that I had set the Preferences for "Everyone" as shown in the image above, in reality, I had overwritten it with a different setting in the "Administrator" Preferences. Specifically, the "Orchestrator Url" under "copilot orchestrator" for "Administrator" was set to localhost. This was not the URL of the container where the orchestrator was running. By removing the "copilot orchestrator" settings for "Administrator" and specifying the correct endpoint of the container running the orchestrator in the "Everyone" settings, it worked correctly. I hope this information is helpful.

@Marcelo Gallardo Hello Marcelo, I've decided to use OpenAI's embeddings for the data loader for now. Could you please explain the specific configuration method for the .env file of the orchestrator? I'm using Ollama as the interface, set up to be usable as an OpenAI-compatible API. I'm using the Llama3 model. No API key is required. Best regards,

Hello Markku, I'm experiencing the same issue. Ollama functions as an OpenAI API-compatible service, but it's generating an error related to the API key. The error message is as follows: ERROR: Exception in ASGI application Traceback (most recent call last): File "/app/main.py", line 208, in handle_request process_docs(docs=docs, vectordb=vector_db) File "/app/main.py", line 89, in process_docs raise e File "/app/main.py", line 85, in process_docs vectordb.add_documents(chuncked_docs) File "/usr/local/lib/python3.10/site-packages/langchain_core/vectorstores.py", line 138, in add_documents return self.add_texts(texts, metadatas, **kwargs) File "/usr/local/lib/python3.10/site-packages/langchain_community/vectorstores/milvus.py", line 558, in add_texts embeddings = self.embedding_func.embed_documents(texts) File "/usr/local/lib/python3.10/site-packages/langchain_openai/embeddings/base.py", line 517, in embed_documents return self._get_len_safe_embeddings(texts, engine=engine) File "/usr/local/lib/python3.10/site-packages/langchain_openai/embeddings/base.py", line 333, in getlen_safe_embeddings response = self.client.create( File "/usr/local/lib/python3.10/site-packages/openai/resources/embeddings.py", line 113, in create return self._post( File "/usr/local/lib/python3.10/site-packages/openai/_base_client.py", line 1232, in post return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)) File "/usr/local/lib/python3.10/site-packages/openai/_base_client.py", line 921, in request return self._request( File "/usr/local/lib/python3.10/site-packages/openai/_base_client.py", line 1012, in _request raise self._make_status_error_from_response(err.response) from None openai.AuthenticationError: Error code: 401 - {'error': {'message': 'Incorrect API key provided: dummy. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}} The version of Copilot I'm using is 1.1.0. Best regards,

I would like to discuss an error in Spotfire Copilot. An error occurred when submitting a question from the panel in Spotfire Copilot. I am sending you a Python log of the error. How should I deal with this? Copilot Version : 1.1.0 INFO:orchestrator-chains:Creating Chat History... INFO:orchestrator-chains:Executing Contextual Chat Chain... INFO:orchestrator-chains:Request Config system prompt: Your role is an expert Spotfire user, explaining features to new users of Spotfire. Assume the user has no prior knowledge of Spotfire and its capabilities. Your purpose is: * To answer the user's HowTo questions - i.e. how to perform tasks in Spotfire * To answer the user's questions regarding the capabilities of Spotfire Be sure to explain in exquisite detail how to perform the action in Spotfire. If Spotfire does not have the capability that the user is asking for, explain this. Answer EXCLUSIVELY using the facts listed in the context below. IMPORTANT: List the sources used in a single list at the end of the response under the heading "Citations:", in the following format: [id::document name::page number] Sources are referenced below in the following format: [id::document name::page number]::: Use square brackets to reference the source, e.g. [1], and use them inline in your response. Context: {context} Reminder: IMPORTANT: List the sources used in a single list at the end of the response under the heading "Citations:", in the following format: [id::document name::page number] Your role is a Spotfire data analysis expert. If the human asks to suggest a visualization, or you suggest creating a visualization, use the Category of the columns found in the metadata to suggest a suitable visualization_type. Do not respond with an answer such as "As an AI language model, I am unable to...". Provide an RFC8259 compliant JSON response following this format without deviation, without mentioning the JSON and without commenting on the JSON itself. Each JSON response MUST be surrounded with " ", and must be indented appropriately Make sure the systemPrompts key and its value are included, exactly as below: JSON: { "operations": [{ "operationTarget": "user", "operationType": "Create Visualization", "operationParameters": { "visualizationType": "visualizationType", "x_expression": "x_expression", "y_expressions": ["y_expression1", "y_expression2"], "dataTable": "dataTable", "colorExpression": "colorExpression", "orientation": "vertical", "sorted": "false" } } ] } Substitute each value of parameters for the "Create Visualization" operationType according to these instructions: * visualizationType: determined by the metadata Category values of the columns selected. Choose among the following values: barchart, linechart, scatterplot. * dataTable: the name of the data table, which MUST chosen appropriately from the metadata below * x_expression, y_expressions and colorExpression (we may refer to them generically as Spotfire custom expressions, or Spotfire expressions, or expressions): Each expression must be a valid Spotfire custom expression. All expressions MUST only use columns associated with the selected dataTable. Each expression requires column names to be enclosed within '[' and ']'. Categorical expressions must be enclosed within '<' at the beginning and '>' at the end. If you suggest multiple columns in a categorical expression, the expression must use the Spotfire "NEST" syntax. For example: "<[Least Detailed Column] NEST [Next Least Detailed Column] NEST [Most Detailed Column]>" * x_expression: an expression for the X axis. Must be a valid Spotfire categorical or continuous custom expression. Remember to use the BinByDateTime function if the expression references a column categorized as "Time", or the AutoBinNumeric function if the expression references a column categorized as "Numbers". Example expression using the BinByDateTime function: <BinByDateTime([column name],"Year.Quarter.Month",2)> Example expression using the AutoBinNumeric function: <AutoBinNumeric([column name], 10)> * y_expressions: one or more expressions for the Y axis. Each of the y_expressions must be a valid Spotfire CONTINUOUS custom expression. If you are recommending a bar chart, each y expression MUST have a suitable aggregation method. * colorExpression - optional, unless there are multiple y_expressions. If you suggest multiple y_expressions, the colorExpression MUST be set to <[Axis.Default.Names]>. * orientation - optional; used for bar charts only. Do NOT swap the axis expressions if the orientation is "horizontal". The x_expression is ALWAYS on the Categorical Axis. y_expressions are ALWAYS on the Value Axis and MUST be CONTINUOUS expressions. * sorted - set to true if you recommend a bar chart and the user is asking a question where a sorted bar chart would be appropriate. Further instructions that depend on the selected visualizationType: * Bar chart: You MUST use an Aggregation method other than (None) for the y_expressions - please choose the most appropriate from Sum, Avg, Min, Max, etc. if asked to provide a count, use the appropriate Spotfire expression, which is count(). You should be aware of the basic Spotfire functions to use in custom expressions. In addition to your role as a general Spotfire expert, your role is to check the metadata in the Spotfire analysis for common errors. Right now, you can only detect if a column that has been loaded as the correct Time category. IMPORTANT: If and only if the name of a column indicates it contains Date or DateTime data but the column is not of category "Time" or in the metadata, perform the following 3 steps (indicated with asterisks): * Warn the user that the data in that column is not of the expected type, and they should fix it by reloading the data with the correct types, or adding a "Calculate and replace column" data transformation to replace the column. * Inform the user that, for now, they can adjust the expression used. IMPORTANT: the expression in any Create_Visualization JSON, where the column is not of the correct category, JSON MUST be of the form: <BinByDateTime(Date([column name]), "Year.Quarter.Month",2)> * Reply with an additional JSON snippet using the following structure, surrounded by " ": { "operations":[ { "operationTarget":"user", "operationType":"Calculate and Replace Column", "operationParameters":{ "data_table":"data_table", "column_name":"column_name", "expression":"expression" } } ] } Replace the values for the operationParameters this way: - data_table: the name of the data table to which the column belongs - column_name: the name of the column in question - expression: the Spotfire custom expression to convert the data type of the original column - for example, "Date([Column Name])" to convert a string type column containing containing date information to a Date Type column. } 2. The following metadata (in JSON format) contains a list of tables and associated columns that exist in the current Spotfire analysis file. This metadata can be used when answering questions. Each column has a Name, Type and Category: [{"TableName":"Chip_sample","ColumnsGroupedByCategoryAndType":[{"Category":"Numbers","Type":"Integer","ColumnNames":["WAFERNO","X","Y"]},{"Category":"Categories","Type":"String","ColumnNames":["LOT","BIN"]},{"Category":"Identifiers","Type":"Integer","ColumnNames":["CHIP_ID"]}]}] INFO: 10.110.2.239:26928 - "POST /orchestrator HTTP/1.1" 500 Internal Server Error ERROR: Exception in ASGI application Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 407, in run_asgi result = await app( # type: ignore[func-returns-value] File "/usr/local/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 69, in __call__ return await self.app(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/fastapi/applications.py", line 1054, in __call__ await super().__call__(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/applications.py", line 123, in __call__ await self.middleware_stack(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 186, in __call__ raise exc File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 164, in __call__ await self.app(scope, receive, _send) File "/usr/local/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 65, in __call__ await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app raise exc File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 756, in __call__ await self.middleware_stack(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 776, in app await route.handle(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 297, in handle await self.app(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 77, in app await wrap_app_handling_exceptions(app, request)(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app raise exc File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 72, in app response = await func(request) File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 278, in app raw_response = await run_endpoint_function( File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 193, in run_endpoint_function return await run_in_threadpool(dependant.call, **values) File "/usr/local/lib/python3.10/site-packages/starlette/concurrency.py", line 42, in run_in_threadpool return await anyio.to_thread.run_sync(func, *args) File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2144, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, *args) File "/app/main-openai.py", line 291, in handle_request result = chains.executeChain(orch_config) File "/app/chains.py", line 289, in executeChain result = __executeContextualChatChain( File "/app/chains.py", line 119, in __executeContextualChatChain prompt=PromptTemplate( File "/usr/local/lib/python3.10/site-packages/pydantic/v1/main.py", line 341, in __init__ raise validation_error pydantic.v1.error_wrappers.ValidationError: 1 validation error for PromptTemplate __root__ Single '}' encountered in format string (type=value_error)

Hi Team, I'd like to consult about a Python error I encountered while working with a "Data Loader" that utilizes Azure Blob and Azure AI Search. I started the Data Loader using the "docker-compose-azblob-azcog.yml" file. When I executed the /load endpoint, the following error occurred: INFO: Started server process [1] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit) INFO: 10.110.140.161:54405 - "GET / HTTP/1.1" 200 OK INFO: 10.110.140.161:54405 - "GET /favicon.ico HTTP/1.1" 404 Not Found INFO: 10.110.140.161:54406 - "GET /docs HTTP/1.1" 200 OK email-validator not installed, email fields will be treated as str. To install, run: pip install email-validator INFO: 10.110.140.161:54406 - "GET /openapi.json HTTP/1.1" 200 OK (trapped) error reading bcrypt version Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/passlib/handlers/bcrypt.py", line 620, in _load_backend_mixin version = _bcrypt.__about__.__version__ AttributeError: module 'bcrypt' has no attribute '__about__' INFO: 10.110.140.161:54408 - "POST /token HTTP/1.1" 200 OK INFO: 10.110.140.161:54439 - "POST /load/ HTTP/1.1" 500 Internal Server Error ERROR: Exception in ASGI application Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/langchain_community/document_loaders/azure_blob_storage_file.py", line 26, in load from azure.storage.blob import BlobClient ModuleNotFoundError: No module named 'azure' The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/app/main.py", line 371, in handle_request docs = loader.load() File "/usr/local/lib/python3.10/site-packages/langchain_community/document_loaders/azure_blob_storage_file.py", line 28, in load raise ImportError( ImportError: Could not import azure storage blob python package. Please install it with pip install azure-storage-blob. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 407, in run_asgi result = await app( # type: ignore[func-returns-value] File "/usr/local/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 69, in __call__ return await self.app(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/fastapi/applications.py", line 1054, in __call__ await super().__call__(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/applications.py", line 123, in __call__ await self.middleware_stack(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 186, in __call__ raise exc File "/usr/local/lib/python3.10/site-packages/starlette/middleware/errors.py", line 164, in __call__ await self.app(scope, receive, _send) File "/usr/local/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 65, in __call__ await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app raise exc File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 756, in __call__ await self.middleware_stack(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 776, in app await route.handle(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 297, in handle await self.app(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 77, in app await wrap_app_handling_exceptions(app, request)(scope, receive, send) File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 64, in wrapped_app raise exc File "/usr/local/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "/usr/local/lib/python3.10/site-packages/starlette/routing.py", line 72, in app response = await func(request) File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 278, in app raw_response = await run_endpoint_function( File "/usr/local/lib/python3.10/site-packages/fastapi/routing.py", line 193, in run_endpoint_function return await run_in_threadpool(dependant.call, **values) File "/usr/local/lib/python3.10/site-packages/starlette/concurrency.py", line 42, in run_in_threadpool return await anyio.to_thread.run_sync(func, *args) File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2144, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, *args) File "/app/main.py", line 376, in handle_request raise HTTPException(status_code=404, detail=json.dumps(e)) File "/usr/local/lib/python3.10/json/__init__.py", line 231, in dumps return _default_encoder.encode(obj) File "/usr/local/lib/python3.10/json/encoder.py", line 199, in encode chunks = self.iterencode(o, _one_shot=True) File "/usr/local/lib/python3.10/json/encoder.py", line 257, in iterencode return _iterencode(o, 0) File "/usr/local/lib/python3.10/json/encoder.py", line 179, in default raise TypeError(f'Object of type {o.__class__.__name__} ' TypeError: Object of type ImportError is not JSON serializable I'd be happy to provide further information if needed. The following is for your reference. Thank you for your assistance. Copilot Version : 1.1.0 .env (sensitive information masked) LOG_LEVEL=INFO ACCESS_TOKEN_EXPIRE_DAYS=1000 SECRET_KEY="********" HASHED_ADMIN_PASSWORD="********" AZSEARCH_EP="https://[my-search-service-name].search.windows.net" AZSEARCH_KEY="********" AZURE_STORAGE_CONNECTION="https://[my-storage-account-name].blob.core.windows.net/[my-container-name]"

Hi Prashant, Thank you very much for your help. I will try using LocalAI for this. I appreciate your cooperation. Best regards,

Hello, I am looking for guidance on how to configure and deploy an on-premises LLM (e.g., Llama3) with Spotfire Copilot. Specifically, I have two main questions: How should the .env file be configured if we want to use an on-premises LLM instead of a cloud-based LLM like OpenAI? What are the necessary steps and requirements to deploy the on-premises LLM as a service to integrate it with Copilot? Any detailed instructions, best practices, or examples would be greatly appreciated. Thank you!

@Marcelo Gallardo I wanted to apologize for the confusion caused by my earlier posts. After reviewing the issue, I realized that it was due to a configuration error on my part. Thank you all for your patience and assistance in helping me identify the problem. I appreciate your support and understanding. Best regards,

@Marcelo Gallardo Thank you very much for your prompt response. Your support has been invaluable, and I appreciate your assistance in helping us move forward with resolving the issue. Unfortunately, when I reproduced the error from Analyst's Copilot, nothing appeared in the log. Also, there were no changes to the “server.log” of the Spotfire Server due to the Copilot's request. Accessing the swagger UI of Orchestrator from a browser in the same location as the PC on which Analyst is running, the logs were logged successfully. Logs were obtained with “docker compose -f docker-compose-orchestrator.yml logs”. orchestrator | INFO: 10.110.20.32:60768 - "POST /token HTTP/1.1" 200 OK orchestrator | INFO: 10.110.20.32:41874 - "GET / HTTP/1.1" 200 OK orchestrator | INFO: 10.110.7.170:43776 - "GET / HTTP/1.1" 200 OK orchestrator | INFO: 10.110.20.32:41880 - "GET / HTTP/1.1" 200 OK I have also attached the DEBUG logs from the Analyst. Please review them.(Some personal information, such as Google accounts, is masked.) Thank you once again for your cooperation and understanding. Best regards, Naoki Nakamichi Spotfire.Dxp.SupportDiagnostics.log

I encountered an error when trying to use Spotfire Copilot from the Panel. The error details are as follows: Error occurred in ReadCore General error occurred. at System.Threading.Tasks.Task`1.GetResultCore(Boolean waitCompletionNotification) at SpotfireDs.CopilotCustomPanel.CopilotCustomPanelView.ReadCore(String method, String args, CopilotCustomPanel snapshotNode) The orchestrator and data loader on the backend are correctly set up. Additionally, the Spotfire user has administrative privileges. The settings in the Administration Manager are also completed, and the connection to the orchestrator URL from the Analyst is successful. Spotfire version: 14.0.2-HF09 Copilot version: 1.1.0