| import difflib |
| import json |
|
|
| import numpy as np |
| import streamlit as st |
| from pyserini.search.lucene import LuceneSearcher |
|
|
|
|
| def read_json(file_name): |
| with open(file_name, "r") as f: |
| json_data = json.load(f) |
| return json_data |
|
|
|
|
| class SearchApplication: |
| def __init__(self): |
| self.title = "Awesome ChatGPT repositories search" |
|
|
| self.set_page_config() |
| self.searcher = self.set_searcher() |
|
|
| st.header(self.title) |
| col1, col2 = st.columns(2) |
| with col1: |
| self.query = st.text_input("Search English words", value="") |
|
|
| with col2: |
| st.write("#") |
| self.search_button = st.button("🔎") |
|
|
| st.caption( |
| "You can search for open-source software from [500+ " |
| " repositories](https://github.com/taishi-i/awesome-ChatGPT-repositories)." |
| ) |
| st.write("#") |
|
|
| candidate_words_file = "candidate_words.json" |
| candidate_words_json = read_json(candidate_words_file) |
| self.candidate_words = candidate_words_json["candidate_words"] |
|
|
| self.show_popular_words() |
| self.show_search_results() |
|
|
| def set_page_config(self): |
| st.set_page_config( |
| page_title=self.title, |
| page_icon="😎", |
| layout="centered", |
| ) |
|
|
| def set_searcher(self): |
| searcher = LuceneSearcher("indexes/docs") |
| return searcher |
|
|
| def show_popular_words(self): |
| st.caption("Popular words") |
|
|
| word1, word2, word3, word4, word5, word6 = st.columns(6) |
| with word1: |
| button1 = st.button("Prompt") |
| if button1: |
| self.query = "prompt" |
|
|
| with word2: |
| button2 = st.button("Chatbot") |
| if button2: |
| self.query = "chatbot" |
|
|
| with word3: |
| button3 = st.button("Langchain") |
| if button3: |
| self.query = "langchain" |
|
|
| with word4: |
| button4 = st.button("Extension") |
| if button4: |
| self.query = "extension" |
|
|
| with word5: |
| button5 = st.button("LLMs") |
| if button5: |
| self.query = "llms" |
|
|
| with word6: |
| button6 = st.button("API") |
| if button6: |
| self.query = "api" |
|
|
| def show_search_results(self): |
| if self.query or self.search_button: |
| st.write("#") |
|
|
| search_results = self.searcher.search(self.query, k=500) |
| num_search_results = len(search_results) |
| st.write(f"A total of {num_search_results} repositories found.") |
|
|
| if num_search_results > 0: |
|
|
| json_search_results = [] |
| for result in search_results: |
| json_data = json.loads(result.raw) |
| json_search_results.append(json_data) |
|
|
| for json_data in sorted( |
| json_search_results, key=lambda x: x["freq"], reverse=True |
| ): |
|
|
| description = json_data["description"] |
| url = json_data["url"] |
| project_name = json_data["project_name"] |
|
|
| st.write("---") |
| st.subheader(f"[{project_name}]({url})") |
| st.write(description) |
|
|
| info = [] |
| language = json_data["language"] |
| if language is not None and len(language) > 0: |
| info.append(language) |
| else: |
| info.append("Laugage: Unkwown") |
|
|
| license = json_data["license"] |
| if license is not None: |
| info.append(license["name"]) |
| else: |
| info.append("License: Unkwown") |
|
|
| st.caption(" / ".join(info)) |
|
|
| else: |
|
|
| if len(self.query) > 0: |
| scores = [] |
| for candidate_word in self.candidate_words: |
| score = difflib.SequenceMatcher( |
| None, self.query, candidate_word |
| ).ratio() |
| scores.append(score) |
|
|
| num_candidate_words = 6 |
|
|
| indexes = np.argsort(scores)[::-1][:num_candidate_words] |
| suggestions = [self.candidate_words[i] for i in indexes] |
| suggestions = sorted( |
| set(suggestions), key=suggestions.index |
| ) |
| st.caption("Suggestions") |
| for i, word in enumerate(suggestions, start=1): |
| st.write(f"{i}: {word}") |
|
|
|
|
| def main(): |
| SearchApplication() |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
