Semantic Search Weighting in Typesense 0.25
TLDR Gustavo suggested improvements for semantic search in Typesense. Jason confirmed it's under consideration. Gustavo then found the answer in query_by_weights
, though it currently doesn't affect the embedding field.
1
1
Aug 19, 2023 (1 month ago)
Gustavo
08:47 PMq:
${userInput} ${context}`, the result goes too much towards the context and the user input doesn't have enough weight. I need some way to control the exact weight of each term. Perhaps something like
vec:([{ q: "${userInput}", weight: 0.7 }, { q: "${context}", weight: 0.3 }])`.Aug 22, 2023 (1 month ago)
Jason
03:24 AM1
Aug 30, 2023 (1 month ago)
Gustavo
09:35 PMquery_by_weights
), and that's much simpler than what I suggested. 😅Jason
09:58 PMGustavo
09:59 PM1
Typesense
Indexed 2776 threads (79% resolved)
Similar Threads
Issues with Semantic Search in OpenAI Embeddings
Semyon was having issues while creating a schema for semantic search with OpenAI embeddings. Jason gave multiple suggestions for troubleshooting but none of them worked. The error was narrowed down to possibly being related to Semyon's specific OpenAI account or the OpenAI API key. The thread ended with Jason suggesting Semyon to check billing and make a direct API call to OpenAI.
Resolving Issues While Upgrading Typesense Server
Ayush had queries about upgrading their Typesense server and updating collections using auto-embeddings. Kishore Nallan clarified all issues, but later discovered that reindexing of non auto-embedded vector fields only is currently supported during altering.
Implementing OR Query in Typesense for Multiple-Word Search
Md.Riad was seeking assistance on implementing an OR query in Typesense for multiple word search. Jason clarified that Typesense already provides this feature by default and suggested to adjust the `drop_tokens_threshold` to obtain more varied results.