cohere-ai · kyle-cohere · May 29, 2024 · May 29, 2024 · May 29, 2024 · May 29, 2024
diff --git a/notebooks/.DS_Store b/notebooks/.DS_Store
diff --git a/notebooks/.ipynb_checkpoints/Deep_dive_into_RAG_evaluation-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Deep_dive_into_RAG_evaluation-checkpoint.ipynb
diff --git a/notebooks/.ipynb_checkpoints/Document_Parsing_For_Enterprises-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Document_Parsing_For_Enterprises-checkpoint.ipynb
diff --git a/notebooks/.ipynb_checkpoints/RAG_with_Chat_Embed_and_Rerank-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/RAG_with_Chat_Embed_and_Rerank-checkpoint.ipynb
diff --git a/notebooks/.ipynb_checkpoints/Vanilla_Multi_Step_Tool_Use-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Vanilla_Multi_Step_Tool_Use-checkpoint.ipynb
diff --git a/notebooks/.ipynb_checkpoints/Vanilla_RAG-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Vanilla_RAG-checkpoint.ipynb
diff --git a/notebooks/Embed_Jobs_Semantic_Search.ipynb b/notebooks/Embed_Jobs_Semantic_Search.ipynb
diff --git a/notebooks/Embed_Jobs_Serverless_Pinecone_Semantic_Search.ipynb b/notebooks/Embed_Jobs_Serverless_Pinecone_Semantic_Search.ipynb
diff --git a/notebooks/Vanilla_RAG.ipynb b/notebooks/Vanilla_RAG.ipynb
diff --git a/notebooks/Wikipedia_Semantic_Search_With_Cohere_Embeddings_Archives.ipynb b/notebooks/Wikipedia_Semantic_Search_With_Cohere_Embeddings_Archives.ipynb
@@ -10,19 +10,6 @@
     "This notebook contains the starter code to do simple [semantic search](https://txt.cohere.ai/what-is-semantic-search/) on the [Wikipedia embeddings archives](https://txt.cohere.ai/embedding-archives-wikipedia/) published by Cohere. These archives embed Wikipedia sites in multiple languages. In this example, we'll use [Wikipedia Simple English](https://huggingface.co/datasets/Cohere/wikipedia-22-12-simple-embeddings). "
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "IUnwp2cYNnP0"
-   },
-   "outputs": [],
-   "source": [
-    "# Let's install \"cohere<5\" and HF datasets\n",
-    "# TODO: upgrade to \"cohere>5\"",
-"!pip install \"cohere<5\" datasets"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -207,7 +194,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.16"
   }
  },
  "nbformat": 4,

diff --git a/notebooks/agents/Data_Analyst_Agent_Cohere_and_Langchain.ipynb b/notebooks/agents/Data_Analyst_Agent_Cohere_and_Langchain.ipynb
@@ -17,7 +17,7 @@
    "source": [
     "# Tool Use - Simple Data Analyst Agent with Cohere and Langchain\n",
     "\n",
-    "Tool use is a method whichs allows developers to connect Cohere's Command models to external tools like search engines, APIs, databases, and other software tools. Just like how [Retrieval-Augmented Generation (RAG)](https://docs.cohere.com/docs/retrieval-augmented-generation-rag) allows a model to use an external data source to improve factual generation, tool use is a capability that allows retrieving data from multiple sources. But it goes beyond simply retrieving information and is able to use software tools to execute code, or even create entries in a CRM system.\n",
+    "Tool use is a method which allows developers to connect Cohere's Command models to external tools like search engines, APIs, databases, and other software tools. Just like how [Retrieval-Augmented Generation (RAG)](https://docs.cohere.com/docs/retrieval-augmented-generation-rag) allows a model to use an external data source to improve factual generation, tool use is a capability that allows retrieving data from multiple sources. But it goes beyond simply retrieving information and is able to use software tools to execute code, or even create entries in a CRM system.\n",
     "\n",
     "In this notebook, we'll see how we can use two tools to create a simple data analyst agent that is able to search the web and run code in a python interpreter. This agent uses Cohere's Command R+ mode and Langchain.\n",
     "\n",
@@ -92,7 +92,7 @@
    },
    "source": [
     "### Web search\n",
-    "Let's first equip our agent with web search! We can use the Tivaly API for this. Head on to [tavily.com](https://tavily.com) and grab an API key to use here."
+    "Let's first equip our agent with web search! We can use the Tavily API for this. Head on to [tavily.com](https://tavily.com) and grab an API key to use here."
    ]
   },
   {
@@ -390,7 +390,7 @@
     "id": "wZBaxCYeG4Xf"
    },
    "source": [
-    "This is a simple example to get you start. There [are many tools](https://python.langchain.com/docs/integrations/tools/) you can equip your agent with. Once youre comfortable with these ideas, you can also proceed to define your tools (see [Multi-step tool use in Action](https://docs.cohere.com/docs/multi-step-tool-use#multi-step-tool-use-in-action)).\n"
+    "This is a simple example to get you started. There [are many tools](https://python.langchain.com/docs/integrations/tools/) you can equip your agent with. Once you're comfortable with these ideas, you can also proceed to define your tools (see [Multi-step tool use in Action](https://docs.cohere.com/docs/multi-step-tool-use#multi-step-tool-use-in-action)).\n"
    ]
   }
  ],
@@ -413,7 +413,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.16"
   }
  },
  "nbformat": 4,