Merge pull request #46 from arc53/hub-loader-cache

load vectors from DocsHUB

.gitignore

@@ -131,4 +131,6 @@ dmypy.json
 .idea/
 
 # macOS
-.DS_Store
+.DS_Store
+
+application/vectors/

application/app.py

@@ -8,6 +8,7 @@ import faiss
 from langchain import OpenAI
 from langchain.chains import VectorDBQAWithSourcesChain
 from langchain.prompts import PromptTemplate
+import requests
 
 # Redirect PosixPath to WindowsPath on Windows
 import platform
@@ -40,11 +41,13 @@ def api_answer():
     api_key = data["api_key"]
     # check if the vectorstore is set
     if "active_docs" in data:
-        vectorstore = "vectorstores/" + data["active_docs"]
+        vectorstore = "vectors/" + data["active_docs"]
+        if data['active_docs'] == "default":
+            vectorstore = ""
 
     else:
         vectorstore = ""
-    print(vectorstore)
+
 
     # loading the index and the store and the prompt template
     index = faiss.read_index(f"{vectorstore}docs.index")
@@ -73,6 +76,30 @@ def api_answer():
 
     return result
 
+@app.route("/api/docs_check", methods=["POST"])
+def check_docs():
+    # check if docs exist in a vectorstore folder
+    data = request.get_json()
+    vectorstore = "vectors/" + data["docs"]
+    base_path = 'https://raw.githubusercontent.com/arc53/DocsHUB/main/'
+    #
+    if os.path.exists(vectorstore):
+        return {"status": 'exists'}
+    else:
+        r = requests.get(base_path + vectorstore + "docs.index")
+        # save to vectors directory
+        # check if the directory exists
+        if not os.path.exists(vectorstore):
+            os.makedirs(vectorstore)
+
+        with open(vectorstore + "docs.index", "wb") as f:
+            f.write(r.content)
+        # download the store
+        r = requests.get(base_path + vectorstore + "faiss_store.pkl")
+        with open(vectorstore + "faiss_store.pkl", "wb") as f:
+            f.write(r.content)
+
+        return {"status":  'loaded'}
 
 # handling CORS
 @app.after_request

application/static/dist/css/output.css

@@ -680,6 +680,11 @@ video {
   background-color: rgb(59 130 246 / var(--tw-bg-opacity));
 }
 
+.bg-gray-50 {
+  --tw-bg-opacity: 1;
+  background-color: rgb(249 250 251 / var(--tw-bg-opacity));
+}
+
 .bg-gray-900 {
   --tw-bg-opacity: 1;
   background-color: rgb(17 24 39 / var(--tw-bg-opacity));
@@ -695,11 +700,6 @@ video {
   background-color: rgb(229 231 235 / var(--tw-bg-opacity));
 }
 
-.bg-gray-50 {
-  --tw-bg-opacity: 1;
-  background-color: rgb(249 250 251 / var(--tw-bg-opacity));
-}
-
 .p-2 {
   padding: 0.5rem;
 }
@@ -785,6 +785,16 @@ video {
   color: rgb(17 24 39 / var(--tw-text-opacity));
 }
 
+.text-green-500 {
+  --tw-text-opacity: 1;
+  color: rgb(34 197 94 / var(--tw-text-opacity));
+}
+
+.text-red-500 {
+  --tw-text-opacity: 1;
+  color: rgb(239 68 68 / var(--tw-text-opacity));
+}
+
 .opacity-75 {
   opacity: 0.75;
 }
@@ -867,43 +877,6 @@ video {
   --tw-ring-color: rgb(59 130 246 / var(--tw-ring-opacity));
 }
 
-@media (prefers-color-scheme: dark) {
-  .dark\:border-gray-600 {
-    --tw-border-opacity: 1;
-    border-color: rgb(75 85 99 / var(--tw-border-opacity));
-  }
-
-  .dark\:bg-gray-700 {
-    --tw-bg-opacity: 1;
-    background-color: rgb(55 65 81 / var(--tw-bg-opacity));
-  }
-
-  .dark\:text-white {
-    --tw-text-opacity: 1;
-    color: rgb(255 255 255 / var(--tw-text-opacity));
-  }
-
-  .dark\:placeholder-gray-400::-moz-placeholder {
-    --tw-placeholder-opacity: 1;
-    color: rgb(156 163 175 / var(--tw-placeholder-opacity));
-  }
-
-  .dark\:placeholder-gray-400::placeholder {
-    --tw-placeholder-opacity: 1;
-    color: rgb(156 163 175 / var(--tw-placeholder-opacity));
-  }
-
-  .dark\:focus\:border-blue-500:focus {
-    --tw-border-opacity: 1;
-    border-color: rgb(59 130 246 / var(--tw-border-opacity));
-  }
-
-  .dark\:focus\:ring-blue-500:focus {
-    --tw-ring-opacity: 1;
-    --tw-ring-color: rgb(59 130 246 / var(--tw-ring-opacity));
-  }
-}
-
 @media (min-width: 640px) {
   .sm\:my-8 {
     margin-top: 2rem;

application/static/src/choiceChange.js

@@ -1,3 +1,29 @@
-  document.getElementById("select-docs").addEventListener("change", function() {
+
-    localStorage.setItem('activeDocs', this.value)
+function docsIndex() {
-  });
+    // loads latest index from https://raw.githubusercontent.com/arc53/DocsHUB/main/combined.json
+    // and stores it in localStorage
+    fetch('https://raw.githubusercontent.com/arc53/DocsHUB/main/combined.json')
+        .then(response => response.json())
+        .then(data => {
+            console.log('Success:', data);
+            localStorage.setItem("docsIndex", JSON.stringify(data));
+        }
+    )
+
+}
+
+document.getElementById("select-docs").addEventListener("change", function() {
+localStorage.setItem('activeDocs', this.value)
+     fetch('/api/docs_check', {
+         method: 'POST',
+         headers: {
+             'Content-Type': 'application/json',
+         },
+         body: JSON.stringify({docs: this.value}),
+     }).then(response => response.json()).then(
+            data => {
+                console.log('Success:', data);
+            }
+     )
+});
+

application/templates/index.html

@@ -61,12 +61,10 @@ This will return a new DataFrame with all the columns from both tables, and only
           <p class="text-sm">The source code is available on <a href="https://github.com/arc53/docsgpt" class="text-blue-500 hover:text-blue-800">Github</a></p><br>
           <p class="text-sm">Currently It uses python pandas documentation, so it will respond to information relevant to pandas. If you want to train it on different documentation -  <a href="https://github.com/arc53/docsgpt/wiki/How-to-train-on-other-documentation" class="text-blue-500 hover:text-blue-800"> please follow this guide </a></p><br>
           <p class="text-sm">If you want to launch it on your own server - <a href="https://github.com/arc53/docsgpt/wiki/How-to-train-on-other-documentation" class="text-blue-500 hover:text-blue-800"> follow this guide </a></p><br>
-            <label  class="block mb-2 text-sm font-medium text-gray-900">Select pre-loaded documentation</label>
+            <label  class="block mb-2 text-sm font-medium text-gray-900">Select documentation from DocsHUB</label>
             <select id="select-docs" class="bg-gray-50 border border-gray-300 text-gray-900 text-sm rounded-lg focus:ring-blue-500 focus:border-blue-500 block w-full p-2.5">
               <option selected>Choose documentation</option>
-              <option value="ethereum/solidity/">Solidity</option>
+              <option value="default">Default</option>
-              <option value="python/pandas/">Pandas</option>
-              <option value="python/scikit-learn/">scikit-learn</option>
             </select>
         </div>
     </div>
@@ -103,6 +101,35 @@ This will return a new DataFrame with all the columns from both tables, and only
             console.log("apiKey is not set")
             document.getElementById('modal').classList.toggle('hidden')
         }
+        if (localStorage.getItem('docsIndex') === null) {
+            console.log("docsIndex is not set")
+            docsIndex()
+        }
+
+        docsIndex = localStorage.getItem('docsIndex')
+        // create option on select with id select-docs
+        var select = document.getElementById("select-docs");
+        // convert docsIndex to json
+        docsIndex = JSON.parse(docsIndex)
+        // create option for each key in docsIndex
+        for (var key in docsIndex) {
+            var option = document.createElement("option");
+            console.log(key)
+            console.log(docsIndex[key])
+            if (docsIndex[key].name == docsIndex[key].language) {
+                option.text = docsIndex[key].name + " " + docsIndex[key].version;
+                option.value = docsIndex[key].name + "/" + ".project" + "/" + docsIndex[key].version + "/";
+                select.add(option);
+            }
+            else {
+                option.text = docsIndex[key].name + " " + docsIndex[key].version;
+                option.value = docsIndex[key].language + "/" + docsIndex[key].name + "/" + docsIndex[key].version + "/";
+                select.add(option);
+            }
+        }
+
+
+
   </script>
     <script src="{{url_for('static',filename='src/authapi.js')}}"></script>
   <script src="{{url_for('static',filename='src/chat.js')}}"></script>