Knowledge - couldn't create embedding of query: error sending request(s): requesting embeddings - retry limit (5) exceeded:

[sangee2004]

Electron build - 8809ed131d32d

1. Had an assistant with knowledge file - Reunion-Under-The-Stars.pdf
2. Added a travel document as thread knowledge.
3. Asked some queries about travel document that succeeded.
4. Chatted with the assistant and asked bout "what is the story of reunion under star"

This resulted in the following error:

Full message shown in UI:

"Error: ERROR: 2024/09/11 16:37:18 INFO Retrieving sources for query query=\"What is the story of \\\"Reunion Under the Star\\\" about?\" datasets=\"[7oxhy 911]\"\n2024/09/11 16:37:18 DEBUG Using default DSN dsn=\"sqlite:///Users/sangeethahariharan/Library/Application Support/gptscript/knowledge/knowledge.db\"\n2024/09/11 16:37:18 DEBUG Using default VectorDBPath vectordbPath=\"/Users/sangeethahariharan/Library/Application Support/gptscript/knowledge/vector.db\"\n2024/09/11 16:37:18 DEBUG Using embedding model provider provider=openai config=\"{BaseURL:https://gateway-api.gptscript.ai/llm APIKey:REDACTED Model:gpt-4 EmbeddingModel:text-embedding-ada-002 EmbeddingEndpoint:/embeddings APIVersion:2024-02-01 APIType:OPEN_AI AzureOpenAIConfig:{Deployment:}}\"\n2024/09/11 16:37:18 DEBUG Loading retrieval flows from config flows_file=blueprint:context dataset=\"[7oxhy 911]\"\n2024/09/11 16:37:18 DEBUG Query Modifier custom configuration name=enhance config=\"{Model:{OpenAI:{BaseURL:https://gateway-api.gptscript.ai/llm APIKey:REDACTED Model:gpt-4o EmbeddingModel: EmbeddingEndpoint: APIVersion: APIType:OPEN_AI AzureOpenAIConfig:{Deployment:}}}}\"\n2024/09/11 16:37:18 DEBUG Retriever custom configuration name=subquery config=\"{Model:{OpenAI:{BaseURL:https://gateway-api.gptscript.ai/llm APIKey:REDACTED Model:gpt-4o EmbeddingModel: EmbeddingEndpoint: APIVersion: APIType:OPEN_AI AzureOpenAIConfig:{Deployment:}}} Limit:3 TopK:10}\"\n2024/09/11 16:37:18 DEBUG Retriever custom configuration name=bm25 config=\"{TopN:10 K1:1.2 B:0.75 CleanStopWords:[auto]}\"\n2024/09/11 16:37:18 DEBUG Retriever custom configuration name=merge config=\"{TopK:10 Retrievers:[{Name:subquery Weight:0xc00533d0a8 Options:map[limit:3 model:map[openai:map[apiKey:cf390689822aa961:d6d25c608e2d1f7ce44a0f2fea6688a9ddb0cfff836a532d3f27caf3d1901d34 apiType:OPEN_AI baseURL:https://gateway-api.gptscript.ai/llm model:gpt-4o]] topK:10]} {Name:bm25 Weight:0xc00533d0d8 Options:map[b:0.75 cleanStopWords:[auto] k1:1.2 topN:10]}] retrievers:[]}\"\n2024/09/11 16:37:18 DEBUG Postprocessor custom configuration name=similarity config=\"{Threshold:0.4 KeepMin:0}\"\n2024/09/11 16:37:18 DEBUG Postprocessor custom configuration name=reduce config={TopK:10}\n2024/09/11 16:37:18 DEBUG Loaded retrieval flow from config flows_file=blueprint:context dataset=\"[7oxhy 911]\"\n2024/09/11 16:37:18 DEBUG Retrieving content from dataset dataset=\"[7oxhy 911]\" query=\"What is the story of \\\"Reunion Under the Star\\\" about?\"\n2024/09/11 16:37:18 DEBUG Prompting LLM prompt=\"The following query will be used for a vector similarity search.\\nPlease enhance it to improve the semantic similarity search.\\nQuery: \\\"What is the story of \\\"Reunion Under the Star\\\" about?\\\"\\nReply only with the JSON {\\\"result\\\": \\\"<enhanced-query>\\\"}.\\nDo not include anything else in your response and don't use markdown highlighting or formatting, just raw JSON.\"\n2024/09/11 16:37:19 DEBUG Modified queries before=\"[What is the story of \\\"Reunion Under the Star\\\" about?]\" queryModifier=enhance after=\"[summarize the plot and main events of the book 'Reunion Under the Star']\"\n2024/09/11 16:37:19 DEBUG Updated query set query=\"What is the story of \\\"Reunion Under the Star\\\" about?\" modified_query_set=\"[summarize the plot and main events of the book 'Reunion Under the Star']\" num_queries=1\n2024/09/11 16:37:19 DEBUG Retrieving documents from merging retriever query=\"summarize the plot and main events of the book 'Reunion Under the Star'\" datasetIDs=\"[7oxhy 911]\" where=map[] whereDocument=[]\n2024/09/11 16:37:19 DEBUG Retrieving documents from retriever component=MergingRetriever retriever=subquery\n2024/09/11 16:37:19 DEBUG Prompting LLM prompt=\"The following query will be used for a vector similarity search.\\nIf it is too complex or covering multiple topics or entities, please split it into multiple subqueries.\\nI.e. a comparative query like \\\"What are the differences between cats and dogs?\\\" could be split into subqueries concerning cats and dogs separately.\\nThe resulting subqueries will then be used for separate vector similarity searches.\\nJust changing the phrasing of the input question often won't change the semantic meaning, so those may not be good candidates.\\nLimit the number of subqueries to a maximum of 3 (less is ok).\\nQuery: \\\"summarize the plot and main events of the book 'Reunion Under the Star'\\\"\\nReply with all subqueries in a json list like the following and don't reply with anything else (also don't use any markdown syntax).\\nResponse schema: {\\\"results\\\": [\\\"<subquery-1>\\\", \\\"<subquery-2>\\\"]}\"\n2024/09/11 16:37:19 DEBUG Retrieving documents from retriever component=MergingRetriever retriever=bm25\n2024/09/11 16:37:19 DEBUG Retrieving documents from dataset component=BM25Retriever dataset=7oxhy\n2024/09/11 16:37:19 DEBUG Retrieving documents from dataset component=BM25Retriever dataset=911\n2024/09/11 16:37:19 DEBUG Retrieved documents from retriever retriever=bm25 numDocs=10\n2024/09/11 16:37:20 DEBUG SubqueryQueryRetriever generated subqueries queries=\"summarize the plot of the book 'Reunion Under the Star' | describe the main events of the book 'Reunion Under the Star'\"\n2024/09/11 16:37:20 DEBUG filtering documents where=map[] whereDocument=[]\n2024/09/11 16:43:53 ERROR Failed to retrieve documents from retriever component=MergingRetriever retriever=subquery error=\"couldn't create embedding of query: error sending request(s): requesting embeddings - retry limit (5) exceeded: #1/5: 502 (err: <nil>); #2/5: 400 (err: <nil>)\"\n2024/09/11 16:43:53 failed to retrieve documents for query \"summarize the plot and main events of the book 'Reunion Under the Star'\" using retriever \"merge\": couldn't create embedding of query: error sending request(s): requesting embeddings - retry limit (5) exceeded: #1/5: 502 (err: <nil>); #2/5: 400 (err: <nil>)\n: exit status 1"