New universal API with streaming/blocking endpoints (#990)

Previous title: Add api_streaming extension and update api-example-stream to use it

* Merge with latest main

* Add parameter capturing encoder_repetition_penalty

* Change some defaults, minor fixes

* Add --api, --public-api flags

* remove unneeded/broken comment from blocking API startup. The comment is already correctly emitted in try_start_cloudflared by calling the lambda we pass in.

* Update on_start message for blocking_api, it should say 'non-streaming' and not 'streaming'

* Update the API examples

* Change a comment

* Update README

* Remove the gradio API

* Remove unused import

* Minor change

* Remove unused import

---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>

api-example.py

@@ -1,57 +1,42 @@
-'''
-
-This is an example on how to use the API for oobabooga/text-generation-webui.
-
-Make sure to start the web UI with the following flags:
-
-python server.py --model MODEL --listen --no-stream
-
-Optionally, you can also add the --share flag to generate a public gradio URL,
-allowing you to use the API remotely.
-
-'''
-import json
-
 import requests
 
-# Server address
-server = "127.0.0.1"
+# For local streaming, the websockets are hosted without ssl - http://
+HOST = 'localhost:5000'
+URI = f'http://{HOST}/api/v1/generate'
 
-# Generation parameters
-# Reference: https://huggingface.co/docs/transformers/main_classes/text_generation#transformers.GenerationConfig
-params = {
-    'max_new_tokens': 200,
-    'do_sample': True,
-    'temperature': 0.72,
-    'top_p': 0.73,
-    'typical_p': 1,
-    'repetition_penalty': 1.1,
-    'encoder_repetition_penalty': 1.0,
-    'top_k': 0,
-    'min_length': 0,
-    'no_repeat_ngram_size': 0,
-    'num_beams': 1,
-    'penalty_alpha': 0,
-    'length_penalty': 1,
-    'early_stopping': False,
-    'seed': -1,
-    'add_bos_token': True,
-    'truncation_length': 2048,
-    'ban_eos_token': False,
-    'skip_special_tokens': True,
-    'stopping_strings': [],
-}
+# For reverse-proxied streaming, the remote will likely host with ssl - https://
+# URI = 'https://your-uri-here.trycloudflare.com/api/v1/generate'
 
-# Input prompt
-prompt = "What I would like to say is the following: "
+def run(context):
+    request = {
+        'prompt': prompt,
+        'max_new_tokens': 250,
+        'do_sample': True,
+        'temperature': 1.3,
+        'top_p': 0.1,
+        'typical_p': 1,
+        'repetition_penalty': 1.18,
+        'top_k': 40,
+        'min_length': 0,
+        'no_repeat_ngram_size': 0,
+        'num_beams': 1,
+        'penalty_alpha': 0,
+        'length_penalty': 1,
+        'early_stopping': False,
+        'seed': -1,
+        'add_bos_token': True,
+        'truncation_length': 2048,
+        'ban_eos_token': False,
+        'skip_special_tokens': True,
+        'stopping_strings': []
+    }
 
-payload = json.dumps([prompt, params])
+    response = requests.post(URI, json=request)
 
-response = requests.post(f"http://{server}:7860/run/textgen", json={
-    "data": [
-        payload
-    ]
-}).json()
+    if response.status_code == 200:
+        result = response.json()['results'][0]['text']
+        print(prompt + result)
 
-reply = response["data"][0]
-print(reply)
+if __name__ == '__main__':
+    prompt = "In order to make homemade bread, follow these steps:\n1)"
+    run(prompt)