upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-02 19:07:25 -05:00
Code Issues Packages Projects Releases Wiki Activity

server: return HTTP 400 for invalid embedding requests (#29060)

Browse Source
This commit is contained in:
Sam Malayek
2026-10-01 16:52:43 +02:00
committed by GitHub
parent 2b36825cbc
commit d775ebf363
3 changed files with 24 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-common.cpp
+2 -2
View File
@@ -1008,7 +1008,7 @@ server_tokens tokenize_input_subprompt(const llama_vocab * vocab, mtmd_context *
return server_tokens(tmp, false);
}
} else {
throw std::runtime_error("\"prompt\" elements must be a string, a list of tokens, a JSON object containing a prompt string, or a list of mixed strings & tokens.");
throw std::invalid_argument("\"prompt\" elements must be a string, a list of tokens, a JSON object containing a prompt string, or a list of mixed strings & tokens.");
}
}
@@ -1023,7 +1023,7 @@ std::vector<server_tokens> tokenize_input_prompts(const llama_vocab * vocab, mtm
result.push_back(tokenize_input_subprompt(vocab, mctx, json_prompt, add_special, parse_special, init_opt));
}
if (result.empty()) {
throw std::runtime_error("\"prompt\" must not be empty");
throw std::invalid_argument("\"prompt\" must not be empty");
}
return result;
}