[hotfix] Deep Lake fails on newer version due to hardcode (#6383)

Hot Fixes for Deep Lake [would highly appreciate expedited review]

* deeplake version was hardcoded and since deeplake upgraded the
integration fails with confusing error
* an additional integration test fixed due to embedding function
* Additionally fixed docs for code understanding links after docs
upgraded
* notebook removal of public parameter to make sure code understanding
notebook works

#### Who can review?
  @hwchase17  @dev2049

---------

Co-authored-by: Davit Buniatyan <d@activeloop.ai>

docs/extras/use_cases/code/index.mdx

@@ -22,5 +22,5 @@ Query Understanding: GPT-4 processes user queries, grasping the context and extr
 5. Ask questions: Define a list of questions to ask about the codebase, and then use the ConversationalRetrievalChain to generate context-aware answers. The LLM (GPT-4) generates comprehensive, context-aware answers based on retrieved code snippets and conversation history.
 
 The full tutorial is available below.
-- [Twitter the-algorithm codebase analysis with Deep Lake](code/twitter-the-algorithm-analysis-deeplake.html): A notebook walking through how to parse github source code and run queries conversation.
-- [LangChain codebase analysis with Deep Lake](code/code-analysis-deeplake.html): A notebook walking through how to analyze and do question answering over THIS code base.
+- [Twitter the-algorithm codebase analysis with Deep Lake](./twitter-the-algorithm-analysis-deeplake.html): A notebook walking through how to parse github source code and run queries conversation.
+- [LangChain codebase analysis with Deep Lake](./code-analysis-deeplake.html): A notebook walking through how to analyze and do question answering over THIS code base.

docs/extras/use_cases/code/twitter-the-algorithm-analysis-deeplake.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -29,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -45,7 +46,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -61,6 +62,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -78,6 +80,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -86,7 +89,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -105,6 +108,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -124,6 +128,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -140,12 +145,12 @@
     "db = DeepLake(\n",
     "    dataset_path=f\"hub://{username}/twitter-algorithm\",\n",
     "    embedding_function=embeddings,\n",
-    "    public=True,\n",
-    ")  # dataset would be publicly available\n",
+    ")\n",
     "db.add_documents(texts)"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -155,9 +160,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deep Lake Dataset in hub://davitbun/twitter-algorithm already exists, loading from the storage\n"
+     ]
+    }
+   ],
    "source": [
     "db = DeepLake(\n",
     "    dataset_path=\"hub://davitbun/twitter-algorithm\",\n",
@@ -168,7 +181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -180,6 +193,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -188,7 +202,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -208,7 +222,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -391,6 +405,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": []
@@ -412,7 +427,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.0"
+   "version": "3.9.7"
   }
  },
  "nbformat": 4,

langchain/vectorstores/deeplake.py

@@ -8,6 +8,7 @@ import numpy as np
 
 try:
     import deeplake
+    from deeplake.core.fast_forwarding import version_compare
     from deeplake.core.vectorstore import DeepLakeVectorStore
 
     _DEEPLAKE_INSTALLED = True
@@ -124,11 +125,11 @@ class DeepLake(VectorStore):
                 "Please install it with `pip install deeplake`."
             )
 
-        version = deeplake.__version__
-        if version != "3.6.2":
+        if version_compare(deeplake.__version__, "3.6.2") == -1:
             raise ValueError(
-                "deeplake version should be = 3.6.3, but you've installed"
-                f" {version}. Consider changing deeplake version to 3.6.3 ."
+                "deeplake version should be >= 3.6.3, but you've installed"
+                f" {deeplake.__version__}. Consider upgrading deeplake version \
+                    pip install --upgrade deeplake."
             )
         self.dataset_path = dataset_path
 
@@ -303,6 +304,9 @@ class DeepLake(VectorStore):
             )
 
         if embedding_function:
+            if isinstance(embedding_function, Embeddings):
+                _embedding_function = embedding_function.embed_query
+            else:
                 _embedding_function = embedding_function
         elif self._embedding_function:
             _embedding_function = self._embedding_function.embed_query