File size: 8,634 Bytes
ed4d993
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
227
228
229
230
231
232
233
234
235
import logging
import re
from typing import List, Optional

from langchain.chains import LLMChain
from langchain.chains.prompt_selector import ConditionalPromptSelector
from langchain_core.callbacks import (
    AsyncCallbackManagerForRetrieverRun,
    CallbackManagerForRetrieverRun,
)
from langchain_core.documents import Document
from langchain_core.language_models import BaseLLM
from langchain_core.output_parsers import BaseOutputParser
from langchain_core.prompts import BasePromptTemplate, PromptTemplate
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_core.retrievers import BaseRetriever
from langchain_core.vectorstores import VectorStore
from langchain_text_splitters import RecursiveCharacterTextSplitter, TextSplitter

from langchain_community.document_loaders import AsyncHtmlLoader
from langchain_community.document_transformers import Html2TextTransformer
from langchain_community.llms import LlamaCpp
from langchain_community.utilities import GoogleSearchAPIWrapper

logger = logging.getLogger(__name__)


class SearchQueries(BaseModel):
    """Search queries to research for the user's goal."""

    queries: List[str] = Field(
        ..., description="List of search queries to look up on Google"
    )


DEFAULT_LLAMA_SEARCH_PROMPT = PromptTemplate(
    input_variables=["question"],
    template="""<<SYS>> \n You are an assistant tasked with improving Google search \
results. \n <</SYS>> \n\n [INST] Generate THREE Google search queries that \
are similar to this question. The output should be a numbered list of questions \
and each should have a question mark at the end: \n\n {question} [/INST]""",
)

DEFAULT_SEARCH_PROMPT = PromptTemplate(
    input_variables=["question"],
    template="""You are an assistant tasked with improving Google search \
results. Generate THREE Google search queries that are similar to \
this question. The output should be a numbered list of questions and each \
should have a question mark at the end: {question}""",
)


class QuestionListOutputParser(BaseOutputParser[List[str]]):
    """Output parser for a list of numbered questions."""

    def parse(self, text: str) -> List[str]:
        lines = re.findall(r"\d+\..*?(?:\n|$)", text)
        return lines


class WebResearchRetriever(BaseRetriever):
    """`Google Search API` retriever."""

    # Inputs
    vectorstore: VectorStore = Field(
        ..., description="Vector store for storing web pages"
    )
    llm_chain: LLMChain
    search: GoogleSearchAPIWrapper = Field(..., description="Google Search API Wrapper")
    num_search_results: int = Field(1, description="Number of pages per Google search")
    text_splitter: TextSplitter = Field(
        RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=50),
        description="Text splitter for splitting web pages into chunks",
    )
    url_database: List[str] = Field(
        default_factory=list, description="List of processed URLs"
    )
    trust_env: bool = Field(
        False,
        description="Whether to use the http_proxy/https_proxy env variables or "
        "check .netrc for proxy configuration",
    )

    @classmethod
    def from_llm(
        cls,
        vectorstore: VectorStore,
        llm: BaseLLM,
        search: GoogleSearchAPIWrapper,
        prompt: Optional[BasePromptTemplate] = None,
        num_search_results: int = 1,
        text_splitter: RecursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(
            chunk_size=1500, chunk_overlap=150
        ),
        trust_env: bool = False,
    ) -> "WebResearchRetriever":
        """Initialize from llm using default template.

        Args:
            vectorstore: Vector store for storing web pages
            llm: llm for search question generation
            search: GoogleSearchAPIWrapper
            prompt: prompt to generating search questions
            num_search_results: Number of pages per Google search
            text_splitter: Text splitter for splitting web pages into chunks
            trust_env: Whether to use the http_proxy/https_proxy env variables
                or check .netrc for proxy configuration

        Returns:
            WebResearchRetriever
        """

        if not prompt:
            QUESTION_PROMPT_SELECTOR = ConditionalPromptSelector(
                default_prompt=DEFAULT_SEARCH_PROMPT,
                conditionals=[
                    (lambda llm: isinstance(llm, LlamaCpp), DEFAULT_LLAMA_SEARCH_PROMPT)
                ],
            )
            prompt = QUESTION_PROMPT_SELECTOR.get_prompt(llm)

        # Use chat model prompt
        llm_chain = LLMChain(
            llm=llm,
            prompt=prompt,
            output_parser=QuestionListOutputParser(),
        )

        return cls(
            vectorstore=vectorstore,
            llm_chain=llm_chain,
            search=search,
            num_search_results=num_search_results,
            text_splitter=text_splitter,
            trust_env=trust_env,
        )

    def clean_search_query(self, query: str) -> str:
        # Some search tools (e.g., Google) will
        # fail to return results if query has a
        # leading digit: 1. "LangCh..."
        # Check if the first character is a digit
        if query[0].isdigit():
            # Find the position of the first quote
            first_quote_pos = query.find('"')
            if first_quote_pos != -1:
                # Extract the part of the string after the quote
                query = query[first_quote_pos + 1 :]
                # Remove the trailing quote if present
                if query.endswith('"'):
                    query = query[:-1]
        return query.strip()

    def search_tool(self, query: str, num_search_results: int = 1) -> List[dict]:
        """Returns num_search_results pages per Google search."""
        query_clean = self.clean_search_query(query)
        result = self.search.results(query_clean, num_search_results)
        return result

    def _get_relevant_documents(
        self,
        query: str,
        *,
        run_manager: CallbackManagerForRetrieverRun,
    ) -> List[Document]:
        """Search Google for documents related to the query input.

        Args:
            query: user query

        Returns:
            Relevant documents from all various urls.
        """

        # Get search questions
        logger.info("Generating questions for Google Search ...")
        result = self.llm_chain({"question": query})
        logger.info(f"Questions for Google Search (raw): {result}")
        questions = result["text"]
        logger.info(f"Questions for Google Search: {questions}")

        # Get urls
        logger.info("Searching for relevant urls...")
        urls_to_look = []
        for query in questions:
            # Google search
            search_results = self.search_tool(query, self.num_search_results)
            logger.info("Searching for relevant urls...")
            logger.info(f"Search results: {search_results}")
            for res in search_results:
                if res.get("link", None):
                    urls_to_look.append(res["link"])

        # Relevant urls
        urls = set(urls_to_look)

        # Check for any new urls that we have not processed
        new_urls = list(urls.difference(self.url_database))

        logger.info(f"New URLs to load: {new_urls}")
        # Load, split, and add new urls to vectorstore
        if new_urls:
            loader = AsyncHtmlLoader(
                new_urls, ignore_load_errors=True, trust_env=self.trust_env
            )
            html2text = Html2TextTransformer()
            logger.info("Indexing new urls...")
            docs = loader.load()
            docs = list(html2text.transform_documents(docs))
            docs = self.text_splitter.split_documents(docs)
            self.vectorstore.add_documents(docs)
            self.url_database.extend(new_urls)

        # Search for relevant splits
        # TODO: make this async
        logger.info("Grabbing most relevant splits from urls...")
        docs = []
        for query in questions:
            docs.extend(self.vectorstore.similarity_search(query))

        # Get unique docs
        unique_documents_dict = {
            (doc.page_content, tuple(sorted(doc.metadata.items()))): doc for doc in docs
        }
        unique_documents = list(unique_documents_dict.values())
        return unique_documents

    async def _aget_relevant_documents(
        self,
        query: str,
        *,
        run_manager: AsyncCallbackManagerForRetrieverRun,
    ) -> List[Document]:
        raise NotImplementedError