File size: 6,998 Bytes
64e9ead f51746a 0d546a3 64e9ead f51746a 0a07b5d 64e9ead 0d546a3 64e9ead f51746a 64e9ead 0d546a3 f51746a 0d546a3 64e9ead f51746a 0d546a3 64e9ead 0d546a3 64e9ead 0d546a3 64e9ead 0d546a3 64e9ead 0d546a3 64e9ead 0d546a3 64e9ead f51746a 64e9ead f51746a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
import os
import re
import langchain
from paperqa import Docs, Settings
import asyncio
#import paperqa
#import paperscraper
from langchain_community.utilities import SerpAPIWrapper
from langchain.base_language import BaseLanguageModel
from langchain.tools import BaseTool
from langchain_openai import OpenAIEmbeddings
from pypdf.errors import PdfReadError
from rdkit import Chem, DataStructs
from rdkit.Chem import AllChem
from langchain_openai import ChatOpenAI
def is_smiles(text):
try:
m = Chem.MolFromSmiles(text, sanitize=False)
if m is None:
return False
return True
except:
return False
def is_multiple_smiles(text):
if is_smiles(text):
return "." in text
return False
def split_smiles(text):
return text.split(".")
import os
import re
import langchain
from paperqa import Docs, Settings
import asyncio
# import paperqa
# import paperscraper
from langchain_community.utilities import SerpAPIWrapper
from langchain.base_language import BaseLanguageModel
from langchain.tools import BaseTool
from langchain_openai import OpenAIEmbeddings
from pypdf.errors import PdfReadError
from rdkit import Chem, DataStructs
from rdkit.Chem import AllChem
import nest_asyncio
from langchain_openai import ChatOpenAI
nest_asyncio.apply()
def is_smiles(text):
try:
m = Chem.MolFromSmiles(text, sanitize=False)
if m is None:
return False
return True
except:
return False
def is_multiple_smiles(text):
if is_smiles(text):
return "." in text
return False
def split_smiles(text):
return text.split(".")
def paper_scraper(search: str, pdir: str = "query", semantic_scholar_api_key: str = None) -> dict:
try:
return paperscraper.search_papers(
search,
pdir=pdir,
semantic_scholar_api_key=semantic_scholar_api_key,
)
except KeyError:
return {}
# def paper_search(llm, query, semantic_scholar_api_key=None):
# prompt = langchain.prompts.PromptTemplate(
# input_variables=["question"],
# template="""
# I would like to find scholarly papers to answer
# this question: {question}. Your response must be at
# most 10 words long.
# 'A search query that would bring up papers that can answer
# this question would be: '""",
# )
# query_chain = langchain.chains.llm.LLMChain(llm=llm, prompt=prompt)
# if not os.path.isdir("./query"): # todo: move to ckpt
# os.mkdir("query/")
# search = query_chain.invoke(query)
# print("\nSearch:", search)
# papers = paper_scraper(search['text'], semantic_scholar_api_key=semantic_scholar_api_key)
# return papers
# async def scholar2result_llm(llm, query, k=5, max_sources=2, openai_api_key=None, semantic_scholar_api_key=None):
# """Useful to answer questions that require
# technical knowledge. Ask a specific question."""
# papers = paper_search(llm, query, semantic_scholar_api_key=semantic_scholar_api_key)
# if len(papers) == 0:
# return "Not enough papers found"
# docs = Docs()
# settings = Settings()
# settings.llm = llm
# not_loaded = 0
# for path, data in papers.items():
# try:
# await docs.aadd(path)
# except (ValueError, FileNotFoundError, PdfReadError):
# not_loaded += 1
# if not_loaded > 0:
# print(f"\nFound {len(papers.items())} papers but couldn't load {not_loaded}.")
# else:
# print(f"\nFound {len(papers.items())} papers and loaded all of them.")
# answer = await docs.aquery(query)
# return answer.answer
# class LiteratureSearch(BaseTool):
# name: str = "LiteratureSearch"
# description: str = (
# "Useful to answer questions that require technical "
# "knowledge. Ask a specific question."
# )
# llm: BaseLanguageModel = None
# openai_api_key: str = None
# semantic_scholar_api_key: str = None
# def __init__(self, llm, openai_api_key, semantic_scholar_api_key):
# super().__init__()
# # api keys
# self.openai_api_key = openai_api_key
# self.semantic_scholar_api_key = semantic_scholar_api_key
# self.llm = ChatOpenAI(model="gpt-4o-2024-11-20",openai_api_key=self.openai_api_key,
# base_url=os.getenv("OPENAI_API_BASE"))
# def _run(self, query) -> str:
# os.environ["OPENAI_API_KEY"] = self.openai_api_key
# os.environ["OPENAI_API_BASE"] = os.getenv("OPENAI_API_BASE")
# return asyncio.run(scholar2result_llm(
# self.llm,
# query,
# openai_api_key=self.openai_api_key,
# semantic_scholar_api_key=self.semantic_scholar_api_key
# ))
# async def _arun(self, query) -> str:
# """Use the tool asynchronously."""
# raise NotImplementedError("this tool does not support async")
def web_search(keywords, search_engine="google"):
try:
return SerpAPIWrapper(
serpapi_api_key=os.getenv("SERP_API_KEY"), search_engine=search_engine
).run(keywords)
except:
return "No results, try another search"
class WebSearch(BaseTool):
name: str = "WebSearch"
description: str = (
"Input a specific question, returns an answer from web search. "
"Give more detailed information and use more general features to formulate your questions."
)
serp_api_key: str = None
def __init__(self, serp_api_key: str = None):
super().__init__()
self.serp_api_key = serp_api_key
def _run(self, query: str) -> str:
if not self.serp_api_key:
return (
"No SerpAPI key found. This tool may not be used without a SerpAPI key."
)
return web_search(query)
async def _arun(self, query: str) -> str:
raise NotImplementedError("Async not implemented")
def web_search(keywords, search_engine="google"):
try:
return SerpAPIWrapper(
serpapi_api_key=os.getenv("SERP_API_KEY"), search_engine=search_engine
).run(keywords)
except:
return "No results, try another search"
class WebSearch(BaseTool):
name: str = "WebSearch"
description: str = (
"Input a specific question, returns an answer from web search. "
"Give more detailed information and use more general features to formulate your questions."
)
serp_api_key: str = None
def __init__(self, serp_api_key: str = None):
super().__init__()
self.serp_api_key = serp_api_key
def _run(self, query: str) -> str:
if not self.serp_api_key:
return (
"No SerpAPI key found. This tool may not be used without a SerpAPI key."
)
return web_search(query)
async def _arun(self, query: str) -> str:
raise NotImplementedError("Async not implemented") |