chroma docs (#1012)

docs/modules/prompts/examples/example_selectors.ipynb

@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "8244ff60",
    "metadata": {},
    "outputs": [],
@@ -43,7 +43,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "id": "7c469c95",
    "metadata": {},
    "outputs": [],
@@ -54,7 +54,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 5,
    "id": "0ec6d950",
    "metadata": {},
    "outputs": [],
@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 6,
    "id": "207e55f7",
    "metadata": {},
    "outputs": [],
@@ -105,7 +105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
    "id": "d00b4385",
    "metadata": {},
    "outputs": [
@@ -142,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 8,
    "id": "878bcde9",
    "metadata": {},
    "outputs": [
@@ -168,7 +168,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 9,
    "id": "e4bebcd9",
    "metadata": {},
    "outputs": [
@@ -220,22 +220,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 10,
    "id": "241bfe80",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.prompts.example_selector import SemanticSimilarityExampleSelector\n",
-    "from langchain.vectorstores import FAISS\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.embeddings import OpenAIEmbeddings"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 11,
    "id": "50d0a701",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
    "source": [
     "example_selector = SemanticSimilarityExampleSelector.from_examples(\n",
     "    # This is the list of examples available to select from.\n",
@@ -243,7 +252,7 @@
     "    # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
     "    OpenAIEmbeddings(), \n",
     "    # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
-    "    FAISS, \n",
+    "    Chroma, \n",
     "    # This is the number of examples to produce.\n",
     "    k=1\n",
     ")\n",
@@ -259,7 +268,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 12,
    "id": "4c8fdf45",
    "metadata": {},
    "outputs": [
@@ -284,7 +293,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 13,
    "id": "829af21a",
    "metadata": {
     "scrolled": true
@@ -311,7 +320,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 14,
    "id": "3c16fe23",
    "metadata": {},
    "outputs": [
@@ -347,17 +356,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "id": "ac95c968",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts.example_selector import MaxMarginalRelevanceExampleSelector"
+    "from langchain.prompts.example_selector import MaxMarginalRelevanceExampleSelector\n",
+    "from langchain.vectorstores import FAISS"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "id": "db579bea",
    "metadata": {},
    "outputs": [],
@@ -384,7 +394,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 20,
    "id": "cd76e344",
    "metadata": {},
    "outputs": [
@@ -412,7 +422,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 21,
    "id": "cf82956b",
    "metadata": {},
    "outputs": [
@@ -422,9 +432,6 @@
      "text": [
       "Give the antonym of every input\n",
       "\n",
-      "Input: happy\n",
-      "Output: sad\n",
-      "\n",
       "Input: enthusiastic\n",
       "Output: apathetic\n",
       "\n",
@@ -696,7 +703,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/prompts/examples/few_shot_examples.ipynb

@@ -242,6 +242,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n",
       "Examples most similar to the input: Who was the father of Mary Ball Washington?\n",
       "\n",
       "\n",
@@ -259,7 +261,7 @@
    ],
    "source": [
     "from langchain.prompts.example_selector import SemanticSimilarityExampleSelector\n",
-    "from langchain.vectorstores import FAISS\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.embeddings import OpenAIEmbeddings\n",
     "\n",
     "\n",
@@ -269,7 +271,7 @@
     "    # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
     "    OpenAIEmbeddings(),\n",
     "    # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
-    "    FAISS,\n",
+    "    Chroma,\n",
     "    # This is the number of examples to produce.\n",
     "    k=1\n",
     ")\n",
@@ -328,6 +330,14 @@
     "\n",
     "print(prompt.format(input=\"Who was the father of Mary Ball Washington?\"))"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "84c43b97",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -346,7 +356,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/modules/prompts/examples/prompt_management.ipynb

@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "094229f4",
    "metadata": {},
    "outputs": [],
@@ -81,7 +81,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "ab46bd2a",
    "metadata": {},
    "outputs": [
@@ -91,7 +91,7 @@
        "'Tell me a joke.'"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -104,7 +104,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "c3ad0fa8",
    "metadata": {},
    "outputs": [
@@ -114,7 +114,7 @@
        "'Tell me a funny joke.'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "ba577dcf",
    "metadata": {},
    "outputs": [
@@ -137,7 +137,7 @@
        "'Tell me a funny joke about chickens.'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -162,7 +162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 7,
    "id": "d0a0756c",
    "metadata": {},
    "outputs": [],
@@ -173,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 8,
    "id": "59046640",
    "metadata": {},
    "outputs": [
@@ -183,7 +183,7 @@
        "PromptTemplate(input_variables=['adjective', 'content'], output_parser=None, template='Tell me a {adjective} joke about {content}.', template_format='f-string', validate_template=True)"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -204,7 +204,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "id": "53b41b6a",
    "metadata": {},
    "outputs": [],
@@ -226,7 +226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 10,
    "id": "ba8aabd3",
    "metadata": {},
    "outputs": [
@@ -236,7 +236,7 @@
        "'\\n\\nQuestion: foo\\nAnswer: bar\\n\\nQuestion: 1\\nAnswer: 2\\n'"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -261,7 +261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 11,
    "id": "3eb36972",
    "metadata": {},
    "outputs": [],
@@ -280,7 +280,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 12,
    "id": "80a91d96",
    "metadata": {},
    "outputs": [],
@@ -290,7 +290,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 13,
    "id": "7931e5f2",
    "metadata": {},
    "outputs": [
@@ -343,7 +343,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 14,
    "id": "e710115f",
    "metadata": {},
    "outputs": [],
@@ -353,7 +353,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 15,
    "id": "5bf23a65",
    "metadata": {},
    "outputs": [],
@@ -374,7 +374,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 16,
    "id": "d4036351",
    "metadata": {},
    "outputs": [
@@ -428,7 +428,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 17,
    "id": "7c469c95",
    "metadata": {},
    "outputs": [],
@@ -438,7 +438,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 18,
    "id": "0ec6d950",
    "metadata": {},
    "outputs": [],
@@ -455,7 +455,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 19,
    "id": "207e55f7",
    "metadata": {},
    "outputs": [],
@@ -485,7 +485,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 20,
    "id": "d00b4385",
    "metadata": {},
    "outputs": [
@@ -522,7 +522,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 21,
    "id": "878bcde9",
    "metadata": {},
    "outputs": [
@@ -548,7 +548,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 22,
    "id": "e4bebcd9",
    "metadata": {},
    "outputs": [
@@ -600,22 +600,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 23,
    "id": "241bfe80",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.prompts.example_selector import SemanticSimilarityExampleSelector\n",
-    "from langchain.vectorstores import FAISS\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.embeddings import OpenAIEmbeddings"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 24,
    "id": "50d0a701",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
    "source": [
     "example_selector = SemanticSimilarityExampleSelector.from_examples(\n",
     "    # This is the list of examples available to select from.\n",
@@ -623,7 +632,7 @@
     "    # This is the embedding class used to produce embeddings which are used to measure semantic similarity.\n",
     "    OpenAIEmbeddings(), \n",
     "    # This is the VectorStore class that is used to store the embeddings and do a similarity search over.\n",
-    "    FAISS, \n",
+    "    Chroma, \n",
     "    # This is the number of examples to produce.\n",
     "    k=1\n",
     ")\n",
@@ -639,7 +648,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 25,
    "id": "4c8fdf45",
    "metadata": {},
    "outputs": [
@@ -732,7 +741,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts.example_selector import MaxMarginalRelevanceExampleSelector"
+    "from langchain.prompts.example_selector import MaxMarginalRelevanceExampleSelector\n",
+    "from langchain.vectorstores import FAISS"
    ]
   },
   {
@@ -863,7 +873,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {