vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix tests

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-10-08 11:48:35 +02:00
parent 468551e7a6
commit 3bea2e6a86
4 changed files with 15 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -3249,7 +3249,7 @@ int main(int argc, char ** argv) {
if (!params.api_keys.empty()) {
// for now, if API key is set, web UI is unusable
svr->Get("/", [&](const httplib::Request & req, httplib::Response & res) {
svr->Get("/", [&](const httplib::Request &, httplib::Response & res) {
return res.set_content("Web UI is disabled because API key is set.", "text/html; charset=utf-8");
});
} else {

12
examples/server/tests/features/security.feature
View file

@ -5,7 +5,7 @@ Feature: Security
Background: Server startup with an api key defined
Given a server listening on localhost:8080
And a model file tinyllamas/stories260K.gguf from HF repo ggml-org/models
And a server api key llama.cpp
And a server api key THIS_IS_THE_KEY
Then the server is starting
Then the server is healthy
@ -17,8 +17,8 @@ Feature: Security
Examples: Prompts
| api_key | api_error |
| llama.cpp | no |
| llama.cpp | no |
| THIS_IS_THE_KEY | no |
| THIS_IS_THE_KEY | no |
| hackeme | raised |
| | raised |
@ -33,8 +33,8 @@ Feature: Security
Examples: Prompts
| api_key | api_error |
| llama.cpp | no |
| llama.cpp | no |
| THIS_IS_THE_KEY | no |
| THIS_IS_THE_KEY | no |
| hackme | raised |
Scenario Outline: OAI Compatibility (invalid response formats)
@ -55,7 +55,7 @@ Feature: Security
Scenario Outline: CORS Options
Given a user api key llama.cpp
Given a user api key THIS_IS_THE_KEY
When an OPTIONS request is sent from <origin>
Then CORS header <cors_header> is set to <cors_header_value>

3
examples/server/tests/features/steps/steps.py
View file

@ -1299,7 +1299,8 @@ async def wait_for_slots_status(context,
async with aiohttp.ClientSession(timeout=DEFAULT_TIMEOUT_SECONDS) as session:
while True:
async with await session.get(f'{base_url}/slots', params=params) as slots_response:
headers = {'Authorization': f'Bearer {context.server_api_key}'}
async with await session.get(f'{base_url}/slots', params=params, headers=headers) as slots_response:
status_code = slots_response.status
slots = await slots_response.json()
if context.debug:

2
examples/server/utils.hpp
View file

@ -90,7 +90,7 @@ inline std::string format_chat(const struct llama_model * model, const std::stri
return formatted_chat;
}
std::string llama_get_chat_template(const struct llama_model * model) {
static std::string llama_get_chat_template(const struct llama_model * model) {
std::string template_key = "tokenizer.chat_template";
// call with NULL buffer to get the total size of the string
int32_t res = llama_model_meta_val_str(model, template_key.c_str(), NULL, 0);