Update the version to 0.1.20 (#297)

Signed-off-by: SimFG <[email protected]>

docs/release_note.md

@@ -5,6 +5,23 @@ To read the following content, you need to understand the basic use of GPTCache,
 - [Readme doc](https://github.com/zilliztech/GPTCache)
 - [Usage doc](https://github.com/zilliztech/GPTCache/blob/main/docs/usage.md)
 
+## v0.1.20 (2023.4.26)
+
+1. support the `temperature` param, like openai
+
+A non-negative number of sampling temperature, defaults to 0.
+A higher temperature makes the output more random.
+A lower temperature means a more deterministic and confident output.
+
+2. Add llama adapter
+
+```python
+from gptcache.adapter.llama_cpp import Llama
+
+llm = Llama('./models/7B/ggml-model.bin')
+answer = llm(prompt=question)
+```
+
 ## v0.1.19 (2023.4.24)
 
 1. Add stability sdk adapter (text -> image)

gptcache/adapter/adapter.py

@@ -98,7 +98,7 @@ def adapt(llm_handler, cache_data_convert, update_cache_callback, *args, **kwarg
             if chat_cache.post_process_messages_func is temperature_softmax:
                 return_message = chat_cache.post_process_messages_func(
                     messages=[t[1] for t in cache_answers],
-                    scores = [t[0] for t in cache_answers],
+                    scores=[t[0] for t in cache_answers],
                     temperature=temperature
                 )
             else:

gptcache/adapter/llama_cpp.py

@@ -29,7 +29,7 @@ class Llama(llama_cpp.Llama):
             data_manager=m,
             embedding_func=onnx.to_embeddings
         )
-        llm = LlamaCpp('./models/7B/ggml-model.bin')
+        llm = Llama('./models/7B/ggml-model.bin')
         answer = llm(prompt=question, cache_obj=llm_cache)
     """
     def __call__(

setup.py

@@ -17,7 +17,7 @@ def parse_requirements(file_name: str) -> List[str]:
 setuptools.setup(
     name="gptcache",
     packages=find_packages(),
-    version="0.1.19",
+    version="0.1.20",
     author="SimFG",
     author_email="[email protected]",
     description="GPTCache, a powerful caching library that can be used to speed up and lower the cost of chat "