mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-28 03:51:50 +00:00
TogetherAI RAG (#15846)
This commit is contained in:
Lance Martin
GitHub
parent
a06db53c37
commit
9c871f427b
156
cookbook/together_ai.ipynb
Normal file
156
cookbook/together_ai.ipynb
Normal file
@ -0,0 +1,156 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0fc0309d-4d49-4bb5-bec0-bd92c6fddb28",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Together AI + RAG\n",
|
||||
" \n",
|
||||
"[Together AI](https://python.langchain.com/docs/integrations/llms/together) has a broad set of OSS LLMs via inference API.\n",
|
||||
"\n",
|
||||
"See [here](https://api.together.xyz/playground). We use `\"mistralai/Mixtral-8x7B-Instruct-v0.1` for RAG on the Mixtral paper.\n",
|
||||
"\n",
|
||||
"Download the paper:\n",
|
||||
"https://arxiv.org/pdf/2401.04088.pdf"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d12fb75a-f707-48d5-82a5-efe2d041813c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"! pip install --quiet pypdf chromadb tiktoken openai langchain-together"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9ab49327-0532-4480-804c-d066c302a322",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Load\n",
|
||||
"from langchain_community.document_loaders import PyPDFLoader\n",
|
||||
"\n",
|
||||
"loader = PyPDFLoader(\"~/Desktop/mixtral.pdf\")\n",
|
||||
"data = loader.load()\n",
|
||||
"\n",
|
||||
"# Split\n",
|
||||
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
|
||||
"\n",
|
||||
"text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=0)\n",
|
||||
"all_splits = text_splitter.split_documents(data)\n",
|
||||
"\n",
|
||||
"# Add to vectorDB\n",
|
||||
"from langchain_community.embeddings import OpenAIEmbeddings\n",
|
||||
"from langchain_community.vectorstores import Chroma\n",
|
||||
"\n",
|
||||
"\"\"\"\n",
|
||||
"from langchain_together.embeddings import TogetherEmbeddings\n",
|
||||
"embeddings = TogetherEmbeddings(model=\"togethercomputer/m2-bert-80M-8k-retrieval\")\n",
|
||||
"\"\"\"\n",
|
||||
"vectorstore = Chroma.from_documents(\n",
|
||||
" documents=all_splits,\n",
|
||||
" collection_name=\"rag-chroma\",\n",
|
||||
" embedding=OpenAIEmbeddings(),\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"retriever = vectorstore.as_retriever()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "4efaddd9-3dbb-455c-ba54-0ad7f2d2ce0f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.output_parsers import StrOutputParser\n",
|
||||
"from langchain_core.prompts import ChatPromptTemplate\n",
|
||||
"from langchain_core.pydantic_v1 import BaseModel\n",
|
||||
"from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
|
||||
"\n",
|
||||
"# RAG prompt\n",
|
||||
"template = \"\"\"Answer the question based only on the following context:\n",
|
||||
"{context}\n",
|
||||
"\n",
|
||||
"Question: {question}\n",
|
||||
"\"\"\"\n",
|
||||
"prompt = ChatPromptTemplate.from_template(template)\n",
|
||||
"\n",
|
||||
"# LLM\n",
|
||||
"from langchain_community.llms import Together\n",
|
||||
"\n",
|
||||
"llm = Together(\n",
|
||||
" model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n",
|
||||
" temperature=0.0,\n",
|
||||
" max_tokens=2000,\n",
|
||||
" top_k=1,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# RAG chain\n",
|
||||
"chain = (\n",
|
||||
" RunnableParallel({\"context\": retriever, \"question\": RunnablePassthrough()})\n",
|
||||
" | prompt\n",
|
||||
" | llm\n",
|
||||
" | StrOutputParser()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "88b1ee51-1b0f-4ebf-bb32-e50e843f0eeb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\nAnswer: The architectural details of Mixtral are as follows:\\n- Dimension (dim): 4096\\n- Number of layers (n\\\\_layers): 32\\n- Dimension of each head (head\\\\_dim): 128\\n- Hidden dimension (hidden\\\\_dim): 14336\\n- Number of heads (n\\\\_heads): 32\\n- Number of kv heads (n\\\\_kv\\\\_heads): 8\\n- Context length (context\\\\_len): 32768\\n- Vocabulary size (vocab\\\\_size): 32000\\n- Number of experts (num\\\\_experts): 8\\n- Number of top k experts (top\\\\_k\\\\_experts): 2\\n\\nMixtral is based on a transformer architecture and uses the same modifications as described in [18], with the notable exceptions that Mixtral supports a fully dense context length of 32k tokens, and the feedforward block picks from a set of 8 distinct groups of parameters. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively. This technique increases the number of parameters of a model while controlling cost and latency, as the model only uses a fraction of the total set of parameters per token. Mixtral is pretrained with multilingual data using a context size of 32k tokens. It either matches or exceeds the performance of Llama 2 70B and GPT-3.5, over several benchmarks. In particular, Mixtral vastly outperforms Llama 2 70B on mathematics, code generation, and multilingual benchmarks.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke(\"What are the Architectural details of Mixtral?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "755cf871-26b7-4e30-8b91-9ffd698470f4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Trace: \n",
|
||||
"\n",
|
||||
"https://smith.langchain.com/public/935fd642-06a6-4b42-98e3-6074f93115cd/r"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"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": "3.9.16"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user