adb llms cache

README.md

@@ -4,16 +4,39 @@ emoji: 🚀
 colorFrom: blue
 colorTo: red
 sdk: gradio
-sdk_version: 3.24.1
+sdk_version: 3.24.1ß
 app_file: app.py
 pinned: false
 license: openrail
 ---
+Anaconda + VScode 的Python环境搭建
+https://blog.csdn.net/weixin_43876852/article/details/125793075
+Anaconda配置安装
+https://www.anaconda.com/products/distribution/start-coding-immediately
+langchain
+https://pypi.org/project/langchain/
+onnxruntim官网
+https://onnxruntime.ai/
+解决ERROR: Could not find a version that satisfies the requirement onnxruntime (from versions: none)
+https://blog.csdn.net/ccheiheihei/article/details/125556753
+onnxruntime connect to feed.修改Mac python默认pip源
+https://blog.csdn.net/m0_59550201/article/details/125962316
+https://aiinfra.visualstudio.com/PublicPackages/_artifacts/feed/ORT-Nightly/PyPI/ort-nightly/overview/1.15.0.dev20230404004
+Mac安装了conda后,解决Mac终端的命令行前的(base)问题
+https://blog.csdn.net/gudeng007/article/details/125534180
+conda安装，找不到module
+https://www.cnblogs.com/Li-JT/p/15477737.html
+Anaconda的升级、配置及使用
+https://blog.csdn.net/turui/article/details/127063642
+Jupyter Notebooks in VS Code  /  %%time
+https://code.visualstudio.com/docs/datascience/jupyter-notebooks
 
+pip3 install langchain
+pip3 install redis
 
-| 日期 |   进度 | 备注 |
-| :--: | :--- | :--: |
-|   2023/04/14   |   接入openAI，简单测试。| |
-| 2023/04/15 | &nbsp;&nbsp;熟悉LangChain API。<br> &nbsp;&nbsp;熟悉Chain的概念。 <br> &nbsp;&nbsp;熟悉agent goole search。<br> &nbsp;&nbsp;熟悉Prompt Template。| |
+更新langchain：
+pip3 install --upgrade langchain
+查看安装列表及版本：
+pip3 list
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

llms_cache.py

@@ -0,0 +1,22 @@
+import langchain
+import time
+from langchain.llms import OpenAI
+from langchain.cache import InMemoryCache
+from langchain.cache import SQLiteCache
+from redis import Redis
+from langchain.cache import RedisCache
+
+# InMemoryCache or SQLiteCache or RedisCache
+# use 'rm .langchain.db' to delete db when use SQLiteCache。
+# langchain.llm_cache = InMemoryCache()
+# langchain.llm_cache = SQLiteCache()
+# langchain.llm_cache = RedisCache(redis_=Redis())
+llm = OpenAI(model_name="text-davinci-002", n=2, best_of=2)
+
+start = time.perf_counter()
+print(llm("今日中国新闻有哪些"))
+print("first suspend：", time.perf_counter() - start)
+
+start = time.perf_counter()
+print(llm("今日中国新闻有哪些"))
+print("second suspend：{:0.10f}".format(time.perf_counter() - start))

llms_cache_gpt.py

@@ -0,0 +1,30 @@
+#测试GPTCache，进行精确匹配缓存或基于语义相似性缓存结果
+import langchain
+import gptcache
+import time
+from langchain.llms import OpenAI
+from gptcache.processor.pre import get_prompt
+from gptcache.manager.factory import get_data_manager
+from langchain.cache import GPTCache
+
+llm = OpenAI(model_name="text-davinci-003", n=2, best_of=2)
+
+# Avoid multiple caches using the same file, causing different llm model caches to affect each other
+i = 0
+file_prefix = "data_map"
+
+def init_gptcache_map(cache_obj: gptcache.Cache):
+    global i
+    cache_path = f'{file_prefix}_{i}.txt'
+    cache_obj.init(
+        pre_embedding_func=get_prompt,
+        data_manager=get_data_manager(data_path=cache_path),
+    )
+    i += 1
+
+langchain.llm_cache = GPTCache(init_gptcache_map)
+
+for i in range(20):
+    start = time.perf_counter()
+    prompt = "男生有2人，女生有{:d}人，一共多少人？".format(i)
+    print("男生有2人，女生有{:d}人, {:s}。 suspend: {:0.4f}".format(i, llm(prompt), time.perf_counter() - start))

llms_cache_gpt_similarity.py

@@ -0,0 +1,42 @@
+import langchain
+import gptcache
+import time
+from langchain.llms import OpenAI
+from gptcache.processor.pre import get_prompt
+from gptcache.manager.factory import get_data_manager
+from langchain.cache import GPTCache
+from gptcache.manager import get_data_manager, CacheBase, VectorBase
+from gptcache import Cache
+from gptcache.embedding import Onnx
+from gptcache.similarity_evaluation.distance import SearchDistanceEvaluation
+
+llm = OpenAI(model_name="text-davinci-003")
+
+# Avoid multiple caches using the same file, causing different llm model caches to affect each other
+i = 0
+file_prefix = "data_map_similarity"
+llm_cache = Cache()
+
+
+def init_gptcache_map(cache_obj: gptcache.Cache):
+    global i
+    cache_path = f'{file_prefix}_{i}.txt'
+    onnx = Onnx()
+    cache_base = CacheBase('sqlite')
+    vector_base = VectorBase('faiss', dimension=onnx.dimension)
+    data_manager = get_data_manager(cache_base, vector_base, max_size=10, clean_size=2, data_path=cache_path)
+    cache_obj.init(
+        pre_embedding_func=get_prompt,
+        embedding_func=onnx.to_embeddings,
+        data_manager=data_manager,
+        similarity_evaluation=SearchDistanceEvaluation(),
+    )
+    i += 1
+
+langchain.llm_cache = GPTCache(init_gptcache_map)
+
+%%time
+for i in range(20):
+    start = time.perf_counter()
+    prompt = "男生有2人，女生有{:d}人，一共多少人？".format(i)
+    print("男生有2人，女生有{:d}人, {:s}。 suspend: {:0.4f}".format(i, llm(prompt), time.perf_counter() - start))

llms_cache_option.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model_name=\"text-davinci-002\", n=2, best_of=2, cache=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 5.07 ms, sys: 2.21 ms, total: 7.28 ms\n",
+      "Wall time: 995 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side!'"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 5.11 ms, sys: 2.25 ms, total: 7.36 ms\n",
+      "Wall time: 818 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the chicken cross the road?\\n\\nTo get to the other side.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

llms_cache_option.py

@@ -0,0 +1,6 @@
+from langchain.llms import OpenAI
+
+llm = OpenAI(model_name="text-davinci-002", n=2, best_of=2, cache=False)
+
+%%time
+llm("Tell me a joke")

llms_cache_option_chain.ipynb

@@ -0,0 +1,117 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model_name=\"text-davinci-002\")\n",
+    "no_cache_llm = OpenAI(model_name=\"text-davinci-002\", cache=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.chains.mapreduce import MapReduceChain\n",
+    "\n",
+    "text_splitter = CharacterTextSplitter()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('./txt/poem.txt') as f:\n",
+    "    state_of_the_union = f.read()\n",
+    "texts = text_splitter.split_text(state_of_the_union)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.docstore.document import Document\n",
+    "docs = [Document(page_content=t) for t in texts[:3]]\n",
+    "from langchain.chains.summarize import load_summarize_chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = load_summarize_chain(llm, chain_type=\"map_reduce\", reduce_llm=no_cache_llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Retrying langchain.llms.openai.completion_with_retry.<locals>._completion_with_retry in 4.0 seconds as it raised APIConnectionError: Error communicating with OpenAI.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 367 ms, sys: 39.4 ms, total: 406 ms\n",
+      "Wall time: 34.3 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nA young woman in Suzhou is pining for her lover who has left her. She spends her days drinking and looking at the moon, hoping he will return to her.'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "chain.run(docs)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

llms_fake.py

@@ -0,0 +1,15 @@
+from langchain.llms.fake import FakeListLLM
+from langchain.agents import load_tools
+from langchain.agents import initialize_agent
+from langchain.agents import AgentType
+
+tools = load_tools(tool_names=["python_repl"])
+responses = [
+    "Action: Python REPL\nAction Input: print(2 + 2)",
+    "Final Answer: 4"
+]
+llm = FakeListLLM(responses=responses)
+agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
+
+result = agent.run("55+66")
+print("result:",result)

requirements.txt

@@ -1 +1 @@
-langchain==0.0.139
+langchain==0.0.141

test.py

@@ -0,0 +1,33 @@
+import time
+import asyncio
+
+from langchain.llms import OpenAI
+
+def generate_serially():
+    llm = OpenAI(temperature=0.9)
+    for _ in range(10):
+        resp = llm.generate(["Hello, how are you?"])
+        print(resp.generations[0][0].text)
+
+
+async def async_generate(llm):
+    resp = await llm.agenerate(["Hello, how are you?"])
+    print(resp.generations[0][0].text)
+
+
+async def generate_concurrently():
+    llm = OpenAI(temperature=0.9)
+    tasks = [async_generate(llm) for _ in range(10)]
+    await asyncio.gather(*tasks)
+
+
+s = time.perf_counter()
+# If running this outside of Jupyter, use asyncio.run(generate_concurrently())
+generate_concurrently() 
+elapsed = time.perf_counter() - s
+print('\033[1m' + f"Concurrent executed in {elapsed:0.2f} seconds." + '\033[0m')
+
+s = time.perf_counter()
+generate_serially()
+elapsed = time.perf_counter() - s
+print('\033[1m' + f"Serial executed in {elapsed:0.2f} seconds." + '\033[0m')

txt/poem.txt

@@ -0,0 +1,5 @@
+落拓江湖常载酒，十年重见云英，依然绰约掌中轻。
+灯前才一笑，偷解砑罗裙。
+薄幸萧郎憔悴甚，此身终负卿卿。
+姑苏城上月黄昏。
+绿窗人去住，红粉泪纵横。ß