mirror of https://github.com/hwchase17/langchain
Codebase RAG fireworks (#12597)
parent
481bf6fae6
commit
f6f3ca12e7
@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2023 LangChain, Inc.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
@ -0,0 +1,15 @@
|
||||
# RAG Codellama Fireworks
|
||||
|
||||
TODO: Add context from below links
|
||||
|
||||
https://blog.fireworks.ai/accelerating-code-completion-with-fireworks-fast-llm-inference-f4e8b5ec534a
|
||||
https://blog.fireworks.ai/simplifying-code-infilling-with-code-llama-and-fireworks-ai-92c9bb06e29c
|
||||
|
||||
|
||||
## Environment Setup
|
||||
|
||||
TODO: Add API keys
|
||||
|
||||
FIREWORKS_API_KEY
|
||||
https://python.langchain.com/docs/integrations/llms/fireworks
|
||||
https://app.fireworks.ai/login?callbackURL=https://app.fireworks.ai
|
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,22 @@
|
||||
[tool.poetry]
|
||||
name = "rag-codellama-fireworks"
|
||||
version = "0.1.0"
|
||||
description = ""
|
||||
authors = ["Lance Martin <lance@langchain.dev>"]
|
||||
readme = "README.md"
|
||||
|
||||
[tool.poetry.dependencies]
|
||||
python = ">=3.8.1,<4.0"
|
||||
langchain = ">=0.0.313, <0.1"
|
||||
gpt4all = ">=1.0.8"
|
||||
tiktoken = ">=0.5.1"
|
||||
chromadb = ">=0.4.14"
|
||||
fireworks-ai = ">=0.6.0"
|
||||
|
||||
[tool.langserve]
|
||||
export_module = "rag_codellama_fireworks"
|
||||
export_attr = "chain"
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core"]
|
||||
build-backend = "poetry.core.masonry.api"
|
@ -0,0 +1,46 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "681a5d1e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Run Template"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d774be2a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langserve.client import RemoteRunnable\n",
|
||||
"\n",
|
||||
"rag_app = RemoteRunnable(\"http://localhost:8000/rag-codellama-fireworks\")\n",
|
||||
"rag_app.invoke(\"How can I initialize a ReAct agent?\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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
|
||||
}
|
@ -0,0 +1,3 @@
|
||||
from rag_codellama_fireworks.chain import chain
|
||||
|
||||
__all__ = ["chain"]
|
@ -0,0 +1,71 @@
|
||||
import os
|
||||
|
||||
from git import Repo
|
||||
from langchain.document_loaders.generic import GenericLoader
|
||||
from langchain.document_loaders.parsers import LanguageParser
|
||||
from langchain.embeddings import GPT4AllEmbeddings
|
||||
from langchain.llms.fireworks import Fireworks
|
||||
from langchain.prompts import ChatPromptTemplate
|
||||
from langchain.pydantic_v1 import BaseModel
|
||||
from langchain.schema.output_parser import StrOutputParser
|
||||
from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
|
||||
from langchain.text_splitter import Language, RecursiveCharacterTextSplitter
|
||||
from langchain.vectorstores import Chroma
|
||||
|
||||
# Check API key
|
||||
if os.environ.get("FIREWORKS_API_KEY", None) is None:
|
||||
raise Exception("Missing `FIREWORKS_API_KEY` environment variable.")
|
||||
|
||||
# Load codebase
|
||||
# Set local path
|
||||
repo_path = "/Users/rlm/Desktop/tmp_repo"
|
||||
# Use LangChain as an example
|
||||
repo = Repo.clone_from("https://github.com/langchain-ai/langchain", to_path=repo_path)
|
||||
loader = GenericLoader.from_filesystem(
|
||||
repo_path + "/libs/langchain/langchain",
|
||||
glob="**/*",
|
||||
suffixes=[".py"],
|
||||
parser=LanguageParser(language=Language.PYTHON, parser_threshold=500),
|
||||
)
|
||||
documents = loader.load()
|
||||
|
||||
# Split
|
||||
python_splitter = RecursiveCharacterTextSplitter.from_language(
|
||||
language=Language.PYTHON, chunk_size=2000, chunk_overlap=200
|
||||
)
|
||||
texts = python_splitter.split_documents(documents)
|
||||
|
||||
# Add to vectorDB
|
||||
vectorstore = Chroma.from_documents(
|
||||
documents=texts,
|
||||
collection_name="codebase-rag",
|
||||
embedding=GPT4AllEmbeddings(),
|
||||
)
|
||||
retriever = vectorstore.as_retriever()
|
||||
|
||||
# RAG prompt
|
||||
template = """Answer the question based only on the following context:
|
||||
{context}
|
||||
|
||||
Question: {question}
|
||||
"""
|
||||
prompt = ChatPromptTemplate.from_template(template)
|
||||
|
||||
# Initialize a Fireworks model
|
||||
model = Fireworks(model="accounts/fireworks/models/llama-v2-34b-code-instruct")
|
||||
|
||||
# RAG chain
|
||||
chain = (
|
||||
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
|
||||
| prompt
|
||||
| model
|
||||
| StrOutputParser()
|
||||
)
|
||||
|
||||
|
||||
# Add typing for input
|
||||
class Question(BaseModel):
|
||||
__root__: str
|
||||
|
||||
|
||||
chain = chain.with_types(input_type=Question)
|
Loading…
Reference in New Issue