Gptcache

🎉 Introduction to new functions of GPTCache
1. Add GPTCache api, makes it easier to access other different llm models and applications

python
from gptcache.adapter.api import put, get
from gptcache.processor.pre import get_prompt
from gptcache import cache

cache.init(pre_embedding_func=get_prompt)
put("hello", "foo")
print(get("hello"))


2. Add image generation bootcamp, link: https://github.com/zilliztech/GPTCache/blob/main/docs/bootcamp/openai/image_generation.ipynb

What's Changed
* Update kreciprocal docstring for updated data store interface. by wxywb in https://github.com/zilliztech/GPTCache/pull/225
* Add docstring for openai by shiyu22 in https://github.com/zilliztech/GPTCache/pull/229
* Add `GPTCache api`, makes it easier to access other different llm mod… by SimFG in https://github.com/zilliztech/GPTCache/pull/227
* Avoid Pillow installation for openai chat by jaelgu in https://github.com/zilliztech/GPTCache/pull/230
* Add image generation bootcamp by shiyu22 in https://github.com/zilliztech/GPTCache/pull/231
* Update docstring for similarity evaluation. by wxywb in https://github.com/zilliztech/GPTCache/pull/232
* Reorganized the `__init__` file in the gptcache dir by SimFG in https://github.com/zilliztech/GPTCache/pull/233
* Update the version to `0.1.15` by SimFG in https://github.com/zilliztech/GPTCache/pull/236


**Full Changelog**: https://github.com/zilliztech/GPTCache/compare/0.1.14...0.1.15

What's Changed
* Fix to fail to save the data to cache by SimFG in https://github.com/zilliztech/GPTCache/pull/224


**Full Changelog**: https://github.com/zilliztech/GPTCache/compare/0.1.13...0.1.14

🎉 Introduction to new functions of GPTCache
1. Add openai audio adapter (**experimental**)

python
cache.init(pre_embedding_func=get_file_bytes)

openai.Audio.transcribe(
model="whisper-1",
file=audio_file
)


2. Improve data eviction implementation

In the future, users will have greater flexibility to customize eviction methods, such as by using Redis or Memcached. Currently, the default caching library is cachetools, which provides an in-memory cache. Other libraries are not currently supported, but may be added in the future.


What's Changed
* Add openai audio adapter by shiyu22 in https://github.com/zilliztech/GPTCache/pull/220
* Improve data eviction implementation by SimFG in https://github.com/zilliztech/GPTCache/pull/221
* Update the version to `0.1.13` by SimFG in https://github.com/zilliztech/GPTCache/pull/222


**Full Changelog**: https://github.com/zilliztech/GPTCache/compare/0.1.12...0.1.13

What's Changed
* Add object storage by junjiejiangjjj in https://github.com/zilliztech/GPTCache/pull/213
* Only when the eviction policy is LRU, the data access_time is updated by SimFG in https://github.com/zilliztech/GPTCache/pull/214
* Add logger for gptcache by shiyu22 in https://github.com/zilliztech/GPTCache/pull/216
* The llm request can customize topk search parameters by SimFG in https://github.com/zilliztech/GPTCache/pull/217
* Scalar return emb in ndarray by junjiejiangjjj in https://github.com/zilliztech/GPTCache/pull/218

🎉 Introduction to new functions of GPTCache
1. The llm request can customize topk search parameters
python
openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[
{"role": "user", "content": question},
],
top_k=10,
)



**Full Changelog**: https://github.com/zilliztech/GPTCache/compare/0.1.11...0.1.12

What's Changed
* Add langchain examples by shiyu22 in https://github.com/zilliztech/GPTCache/pull/196
* Enable Python syntax highlighting by Pouyanpi in https://github.com/zilliztech/GPTCache/pull/199
* Add openai Completion adapter by shiyu22 in https://github.com/zilliztech/GPTCache/pull/202
* Add openai bootcamp by shiyu22 in https://github.com/zilliztech/GPTCache/pull/207
* Add openai.Image.create in adapter by jaelgu in https://github.com/zilliztech/GPTCache/pull/208
* Refine scalar storage by junjiejiangjjj in https://github.com/zilliztech/GPTCache/pull/205
* Improve the langchain example by SimFG in https://github.com/zilliztech/GPTCache/pull/211

New Contributors
* Pouyanpi made their first contribution in https://github.com/zilliztech/GPTCache/pull/199

🎉 Introduction to new functions of GPTCache

1. Add openai complete adapter

python
cache.init(pre_embedding_func=get_prompt)

response = openai.Completion.create(
model="text-davinci-003",
prompt=question
)


2. Add langchain and openai [bootcamp](https://github.com/zilliztech/GPTCache/tree/main/docs/bootcamp)

3. Add openai image adapter (**experimental**)

python
from gptcache.adapter import openai

cache.init()
cache.set_openai_key()

prompt1 = 'a cat sitting besides a dog'
size1 = '256x256'

openai.Image.create(
prompt=prompt1,
size=size1,
response_format='b64_json'
)


4. Refine storage interface

**Full Changelog**: https://github.com/zilliztech/GPTCache/compare/0.1.10...0.1.11

What's Changed
* Update CI timeout by binbinlv in https://github.com/zilliztech/GPTCache/pull/190
* Add kreciprocal evaluation. by wxywb in https://github.com/zilliztech/GPTCache/pull/191
* Improve coverage testing by SimFG in https://github.com/zilliztech/GPTCache/pull/194
* Get_scalar_data return emb by junjiejiangjjj in https://github.com/zilliztech/GPTCache/pull/195
* Add chatmodels for langchain by shiyu22 in https://github.com/zilliztech/GPTCache/pull/193


**Full Changelog**: https://github.com/zilliztech/GPTCache/compare/0.1.9...0.1.10