Duplicate from taishi-i/awesome-ChatGPT-repositories-search

Co-authored-by: Taishi Ikeda <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Awesome ChatGPT Repositories Search
+emoji: 🏢
+colorFrom: red
+colorTo: blue
+sdk: streamlit
+sdk_version: 1.17.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: taishi-i/awesome-ChatGPT-repositories-search
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,158 @@
+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()

candidate_words.json

@@ -0,0 +1,775 @@
+{
+    "candidate_words": [
+        "allow",
+        "enabling",
+        "docs",
+        "giving",
+        "interesting",
+        "things",
+        "artificial",
+        "intelligence",
+        "developed",
+        "friendly",
+        "slack",
+        "webpage",
+        "videos",
+        "communicate",
+        "structured",
+        "discord",
+        "ask",
+        "general",
+        "papers",
+        "lecture",
+        "notebooks",
+        "engineering",
+        "promptr",
+        "dynamically",
+        "parse",
+        "apply",
+        "included",
+        "purposes",
+        "creative",
+        "gpt4",
+        "starting",
+        "efficiency",
+        "create",
+        "siri",
+        "continuous",
+        "chain",
+        "created",
+        "want",
+        "23",
+        "switch",
+        "oriented",
+        "branch",
+        "personalized",
+        "taking",
+        "notes",
+        "product",
+        "folks",
+        "sentence",
+        "word",
+        "storage",
+        "experiences",
+        "subtitles",
+        "developers",
+        "jailbreak",
+        "stories",
+        "systems",
+        "kubernetes",
+        "issues",
+        "having",
+        "con",
+        "en",
+        "gui",
+        "moderation",
+        "summarizer",
+        "wechat",
+        "example",
+        "integrate",
+        "databricks",
+        "repl",
+        "basic",
+        "trading",
+        "continuously",
+        "bots",
+        "teach",
+        "phind.com",
+        "chat.openai.com",
+        "etc",
+        "speaker",
+        "multilingual",
+        "wait",
+        "pdf",
+        "corpus",
+        "talk",
+        "deploy",
+        "reflection",
+        "state",
+        "art",
+        "website",
+        "tweets",
+        "specified",
+        "twitter",
+        "post",
+        "fixed",
+        "comment",
+        "resource",
+        "center",
+        "network",
+        "state",
+        "exploring",
+        "macos",
+        "edits",
+        "studio",
+        "sample",
+        "js",
+        "backed",
+        "filesystem",
+        "example",
+        "hackathon",
+        "interact",
+        "voice",
+        "gptchat",
+        "driven",
+        "consumer",
+        "hardware",
+        "aims",
+        "provide",
+        "stream",
+        "3d",
+        "highlighting",
+        "execution",
+        "presets",
+        "joy",
+        "rasa",
+        "built",
+        "fastapi",
+        "figmachain",
+        "html",
+        "css",
+        "interactive",
+        "starter",
+        "find",
+        "ida",
+        "@ykdojo",
+        "decompilation",
+        "user",
+        "coming",
+        "soon",
+        "suite",
+        "add",
+        "endpoints",
+        "urls",
+        "intelligence",
+        "management",
+        "providers",
+        "versatile",
+        "bringing",
+        "browsers",
+        "runs",
+        "cool",
+        "@langchainai",
+        "snippets",
+        "session",
+        "jupyter",
+        "stable",
+        "jupyter",
+        "ipython",
+        "chrome",
+        "generates",
+        "box",
+        "minimal",
+        "google",
+        "manifest",
+        "v3",
+        "summary",
+        "vscode",
+        "browser",
+        "translation",
+        "obsidian",
+        "enhance",
+        "engines",
+        "friends",
+        "vim",
+        "neovim",
+        "assemble",
+        "experiment",
+        "ts",
+        "human",
+        "powered",
+        "perform",
+        "vulnerabilities",
+        "list",
+        "controls",
+        "metatrader",
+        "connect",
+        "softly",
+        "reference",
+        "tokens",
+        "tool",
+        "complex",
+        "agent",
+        "advanced",
+        "processing",
+        "automate",
+        "required",
+        "token",
+        "giving",
+        "nmap",
+        "modules",
+        "great",
+        "memories",
+        "module",
+        "xml",
+        "shows",
+        "main",
+        "purpose",
+        "requests",
+        "impressive",
+        "toolkit",
+        "converts",
+        "prepare",
+        "msg",
+        "hook",
+        "client",
+        "feature",
+        "weight",
+        "database",
+        "reliable",
+        "goal",
+        "online",
+        "feedback",
+        "palm",
+        "architecture",
+        "transformer",
+        "multimodal",
+        "stay",
+        "transformers",
+        "neural",
+        "iclr",
+        "retrieval",
+        "pytorch",
+        "flash",
+        "gptq",
+        "quantization",
+        "adapter",
+        "pre",
+        "apache",
+        "2.0",
+        "implementations",
+        "distilbert",
+        "stablelm",
+        "para",
+        "30",
+        "backend",
+        "microsoft",
+        "biomedical",
+        "literature",
+        "train",
+        "gpt2",
+        "integrated",
+        "bilingual",
+        "benchmark",
+        "citations",
+        "quantized",
+        "llms",
+        "fine",
+        "emails",
+        "camel",
+        "communicative",
+        "mind",
+        "exploration",
+        "society",
+        "problem",
+        "blog",
+        "reading",
+        "languages",
+        "vision",
+        "project",
+        "subtitle",
+        "transform",
+        "json",
+        "world",
+        "best",
+        "led",
+        "evaluation",
+        "predict",
+        "json",
+        "description",
+        "translate",
+        "op",
+        "upload",
+        "locally",
+        "locally",
+        "tuned",
+        "style",
+        "second",
+        "flask",
+        "nice",
+        "following",
+        "github",
+        "siri",
+        "i.e.",
+        "question",
+        "privately",
+        "explain",
+        "neuron",
+        "explanation",
+        "visualization",
+        "galactica",
+        "external",
+        "inference",
+        "names",
+        "control",
+        "completion",
+        "hugging",
+        "face",
+        "supported",
+        "transform",
+        "blip2",
+        "grit",
+        "@openai",
+        "port",
+        "mozilla",
+        "directory",
+        "pure",
+        "package",
+        "benchmarks",
+        "menubar",
+        "app",
+        "dall·e",
+        "automated",
+        "remote",
+        "access",
+        "talking",
+        "fastest",
+        "medium",
+        "sized",
+        "gpts",
+        "networks",
+        "fast",
+        "flexible",
+        "speech",
+        "layer",
+        "web",
+        "talk",
+        "bypass",
+        "effective",
+        "update",
+        "visual",
+        "dl",
+        "deep",
+        "pytorch",
+        "javascript",
+        "high",
+        "server",
+        "flutter",
+        "room",
+        "profile",
+        "automatically",
+        "notification",
+        "quality",
+        "gt",
+        "effects",
+        "vosviewer",
+        "chinese",
+        "curated",
+        "includes",
+        "curated",
+        "apis",
+        "gpt4",
+        "read",
+        "summarize",
+        "youtube",
+        "self",
+        "mode",
+        "blender",
+        "latest",
+        "2023",
+        "generate",
+        "foundation",
+        "makes",
+        "learners",
+        "technology",
+        "w/",
+        "generative",
+        "reverse",
+        "message",
+        "game",
+        "page",
+        "productivity",
+        "javascript",
+        "prompts",
+        "figma",
+        "building",
+        "creating",
+        "useful",
+        "complete",
+        "light",
+        "bug",
+        "bounty",
+        "apple",
+        "speed",
+        "correct",
+        "unofficial",
+        "custom",
+        "machine",
+        "similar",
+        "proof",
+        "concept",
+        "agents",
+        "functions",
+        "let",
+        "hours",
+        "speech",
+        "autogpt",
+        "solution",
+        "human",
+        "test",
+        "comments",
+        "designed",
+        "issue",
+        "history",
+        "experience",
+        "error",
+        "implemented",
+        "langchain",
+        "typescript",
+        "projects",
+        "self",
+        "hosted",
+        "compatible",
+        "cpu",
+        "minimal",
+        "detection",
+        "agi",
+        "response",
+        "streaming",
+        "platform",
+        "llamaindex",
+        "input",
+        "free",
+        "lets",
+        "google",
+        "decompiler",
+        "burp",
+        "instruction",
+        "system",
+        "supports",
+        "inside",
+        "server",
+        "superpowers",
+        "notebook",
+        "diffusion",
+        "link",
+        "editor",
+        "development",
+        "openai",
+        "generator",
+        "deploy",
+        "accomplish",
+        "building",
+        "js",
+        "experimental",
+        "emacs",
+        "ask",
+        "scan",
+        "source",
+        "babyagi",
+        "copilot",
+        "program",
+        "powerful",
+        "qgis",
+        "reverse",
+        "faster",
+        "shell",
+        "english",
+        "integrate",
+        "writes",
+        "native",
+        "php",
+        "multiple",
+        "quick",
+        "sources",
+        "automatic",
+        "rlhf",
+        "reinforcement",
+        "chain",
+        "reasoning",
+        "pre",
+        "nanogpt",
+        "licensed",
+        "c++",
+        "bert",
+        "answering",
+        "base",
+        "deep",
+        "stanford",
+        "generating",
+        "distributed",
+        "transformer",
+        "game",
+        "seconds",
+        "scale",
+        "finetuning",
+        "long",
+        "amp",
+        "activations",
+        "index",
+        "examples",
+        "llama",
+        "bindings",
+        "clone",
+        "check",
+        "simplest",
+        "machine",
+        "macos",
+        "efficient",
+        "configure",
+        "demos",
+        "applications",
+        "chatgpt",
+        "cases",
+        "security",
+        "format",
+        "text",
+        "langchain",
+        "responses",
+        "templates",
+        "official",
+        "engineered",
+        "images",
+        "share",
+        "software",
+        "play",
+        "trained",
+        "telegram",
+        "discord",
+        "swift",
+        "platform",
+        "generating",
+        "gpt-3.5",
+        "cloudflare",
+        "running",
+        "llama.cpp",
+        "sdk",
+        "ios",
+        "helps",
+        "developers",
+        "next.js",
+        "quickly",
+        "plugin",
+        "easily",
+        "queries",
+        "scale",
+        "directly",
+        "automatically",
+        "extension",
+        "results",
+        "plugins",
+        "nlp",
+        "programming",
+        "analysis",
+        "autogpt",
+        "auto",
+        "proxy",
+        "dns",
+        "node.js",
+        "translate",
+        "library",
+        "tuned",
+        "deepspeed",
+        "ml",
+        "performance",
+        "instruction",
+        "dataset",
+        "favorite",
+        "llm",
+        "package",
+        "power",
+        "alternative",
+        "demo",
+        "apps",
+        "resources",
+        "robot",
+        "engineering",
+        "chatbot",
+        "capabilities",
+        "codebase",
+        "bing",
+        "image",
+        "desktop",
+        "turbo",
+        "conversations",
+        "fine",
+        "released",
+        "set",
+        "interact",
+        "style",
+        "conversation",
+        "telegram",
+        "gpu",
+        "time",
+        "easy",
+        "review",
+        "langchain",
+        "dall",
+        "visual",
+        "write",
+        "documentation",
+        "git",
+        "android",
+        "application",
+        "react",
+        "framework",
+        "lines",
+        "agents",
+        "interacting",
+        "unofficial",
+        "github",
+        "simple",
+        "implementation",
+        "official",
+        "gpt-2",
+        "attention",
+        "tuning",
+        "de",
+        "fast",
+        "contains",
+        "backend",
+        "gpt-3",
+        "rust",
+        "python",
+        "way",
+        "desktop",
+        "optimization",
+        "codes",
+        "users",
+        "community",
+        "experimental",
+        "collection",
+        "documents",
+        "gpt3",
+        "knowledge",
+        "key",
+        "version",
+        "work",
+        "video",
+        "gpt4all",
+        "information",
+        "attempt",
+        "application",
+        "enables",
+        "whisper",
+        "support",
+        "script",
+        "generated",
+        "auto",
+        "file",
+        "content",
+        "access",
+        "run",
+        "real",
+        "plugins",
+        "shell",
+        "wrapper",
+        "alpaca",
+        "unity",
+        "fully",
+        "tools",
+        "better",
+        "awesome",
+        "including",
+        "built",
+        "integration",
+        "prompt",
+        "files",
+        "supports",
+        "mac",
+        "linux",
+        "gpt-3.5",
+        "100",
+        "build",
+        "local",
+        "learning",
+        "paper",
+        "answers",
+        "agent",
+        "need",
+        "memory",
+        "chrome",
+        "transformers",
+        "inference",
+        "free",
+        "research",
+        "generation",
+        "uses",
+        "learning",
+        "assistant",
+        "api",
+        "scripts",
+        "pdf",
+        "provides",
+        "list",
+        "model",
+        "build",
+        "gpt-4",
+        "large",
+        "questions",
+        "single",
+        "repository",
+        "voice",
+        "create",
+        "ui",
+        "windows",
+        "messages",
+        "written",
+        "allows",
+        "natural",
+        "chat",
+        "implementation",
+        "new",
+        "project",
+        "use",
+        "search",
+        "tasks",
+        "large",
+        "run",
+        "code",
+        "commands",
+        "autonomous",
+        "training",
+        "gpt",
+        "models",
+        "open",
+        "commit",
+        "llama",
+        "repo",
+        "prompt",
+        "prompts",
+        "cli",
+        "interface",
+        "line",
+        "terminal",
+        "chatbot",
+        "help",
+        "app",
+        "simple",
+        "command",
+        "browser",
+        "text",
+        "generate",
+        "client",
+        "library",
+        "language",
+        "like",
+        "data",
+        "plugin",
+        "extension",
+        "use",
+        "llms",
+        "bot",
+        "web",
+        "gpt-4",
+        "llm",
+        "tool",
+        "powered",
+        "gpt-3",
+        "python",
+        "source",
+        "open",
+        "chat",
+        "chatgpt",
+        "models",
+        "model",
+        "code",
+        "based",
+        "language",
+        "gpt",
+        "ai",
+        "api",
+        "openai",
+        "chatgpt"
+    ]
+}

packages.txt

@@ -0,0 +1 @@
+openjdk-11-jdk

requirements.txt

@@ -0,0 +1,3 @@
+pyserini
+faiss-cpu
+torch