FROM llama2

PARAMETER temperature 1

SYSTEM """
You are Professor Dumbledore. Answer as Dumbledore, the assistant, only give guidance about Hogwarts and wizardry
"""

from langchain_community.llms import Ollama
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

llm = Ollama(model="llama2",
             callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))

llm.invoke("Tell me 5 facts about Roman history:")

from langchain_community.llms import Ollama
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser

llm = Ollama(model="llama2",
             callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),
             temperature=0.9)

prompt = ChatPromptTemplate.from_template("Give me 5 interesting facts about {topic}?")
output_parser = StrOutputParser()

chain = prompt | llm | output_parser

chain.invoke({"topic": "Artificial Intelligence"})

import bs4
from langchain import hub
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import Chroma
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_community.embeddings import OllamaEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.llms import Ollama

llm = Ollama(model="llama2",
             temperature=0)

loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",)
)

docs = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
splits = text_splitter.split_documents(docs)
vectorstore = Chroma.from_documents(documents=splits, embedding=OllamaEmbeddings())

# Retrieve and generate using the relevant snippets of the blog.
retriever = vectorstore.as_retriever()
prompt = hub.pull("rlm/rag-prompt-llama")

def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)

rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

rag_chain.invoke("What is Task Decomposition?")

prompt = hub.pull("rlm/rag-prompt-llama")
prompt.pretty_print()

================================ Human Message =================================

[INST]<<SYS>> You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.<</SYS>> 
Question: {question} 
Context: {context} 
Answer: [/INST]

FROM ./jackalope-7b.Q6_K.gguf

TEMPLATE """{{- if .System }}
<|im_start|>system {{ .System }}<|im_end|>
{{- end }}
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

SYSTEM """"""

PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>

from ollama import chat

messages = [
    {
        "role": "user",
        "content": "Why is the sky blue?"
    }
]

response = chat("mistral", messages=messages, stream=False)
print(response["message"]["content"])

/set system あなたは親切なアシスタントです。
/save test