From 9c32b6b9ed02b89fecc13b406c83288084a55aa0 Mon Sep 17 00:00:00 2001 From: Roy Han Date: Mon, 1 Jul 2024 11:59:44 -0700 Subject: [PATCH] Truncation --- docs/api.md | 19 ------------------- server/routes.go | 2 +- 2 files changed, 1 insertion(+), 20 deletions(-) diff --git a/docs/api.md b/docs/api.md index f1097fd67..35f1def33 100644 --- a/docs/api.md +++ b/docs/api.md @@ -996,25 +996,6 @@ If `stream` is set to `false`, then the response is a single JSON object: { "status": "success" } ``` -```shell -POST /api/embed -``` - -# Parameters -- `model` -- `input`: string or array of strings - - cap on string size and array size - -# Response -- `embeddings`: array of embeddings (array of floats) - - normalized? definitely normalize for openai - - - truncate flag defaults true, otherwise false if doesn't fit - -- deprecate /api/embeddings later - - - ## Generate Embeddings ```shell diff --git a/server/routes.go b/server/routes.go index 5a810b274..b305ddc76 100644 --- a/server/routes.go +++ b/server/routes.go @@ -402,7 +402,7 @@ func (s *Server) EmbedHandler(c *gin.Context) { } if len(tokens) > opts.NumCtx { - tokens = tokens[len(tokens)-opts.NumCtx:] + tokens = tokens[:opts.NumCtx] return runner.llama.Detokenize(c.Request.Context(), tokens) }