Harrison/ngram example (#846)

Co-authored-by: Sean Spriggens <ssprigge@syr.edu>

docs/modules/prompts/examples/example_selectors.ipynb

@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "8244ff60",
    "metadata": {},
    "outputs": [],
@@ -81,7 +81,7 @@
     "    template=\"Input: {input}\\nOutput: {output}\",\n",
     ")\n",
     "example_selector = LengthBasedExampleSelector(\n",
-    "    # These are the examples is has available to choose from.\n",
+    "    # These are the examples it has available to choose from.\n",
     "    examples=examples, \n",
     "    # This is the PromptTemplate being used to format the examples.\n",
     "    example_prompt=example_prompt, \n",
@@ -439,10 +439,242 @@
     "print(similar_prompt.format(adjective=\"worried\"))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "4aaeed2f",
+   "metadata": {},
+   "source": [
+    "## NGram Overlap ExampleSelector\n",
+    "\n",
+    "The NGramOverlapExampleSelector selects and orders examples based on which examples are most similar to the input, according to an ngram overlap score. The ngram overlap score is a float between 0.0 and 1.0, inclusive. \n",
+    "\n",
+    "The selector allows for a threshold score to be set. Examples with an ngram overlap score less than or equal to the threshold are excluded. The threshold is set to -1.0, by default, so will not exclude any examples, only reorder them. Setting the threshold to 0.0 will exclude examples that have no ngram overlaps with the input.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9cbc0acc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.prompts.example_selector.ngram_overlap import NGramOverlapExampleSelector"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4f318f4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# These are examples of a fictional translation task.\n",
+    "examples = [\n",
+    "    {\"input\": \"See Spot run.\", \"output\": \"Ver correr a Spot.\"},\n",
+    "    {\"input\": \"My dog barks.\", \"output\": \"Mi perro ladra.\"},\n",
+    "    {\"input\": \"Spot can run.\", \"output\": \"Spot puede correr.\"},\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "bf75e0fe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "example_prompt = PromptTemplate(\n",
+    "    input_variables=[\"input\", \"output\"],\n",
+    "    template=\"Input: {input}\\nOutput: {output}\",\n",
+    ")\n",
+    "example_selector = NGramOverlapExampleSelector(\n",
+    "    # These are the examples it has available to choose from.\n",
+    "    examples=examples, \n",
+    "    # This is the PromptTemplate being used to format the examples.\n",
+    "    example_prompt=example_prompt, \n",
+    "    # This is the threshold, at which selector stops.\n",
+    "    # It is set to -1.0 by default.\n",
+    "    threshold=-1.0,\n",
+    "    # For negative threshold:\n",
+    "    # Selector sorts examples by ngram overlap score, and excludes none.\n",
+    "    # For threshold greater than 1.0:\n",
+    "    # Selector excludes all examples, and returns an empty list.\n",
+    "    # For threshold equal to 0.0:\n",
+    "    # Selector sorts examples by ngram overlap score,\n",
+    "    # and excludes those with no ngram overlap with input.\n",
+    ")\n",
+    "dynamic_prompt = FewShotPromptTemplate(\n",
+    "    # We provide an ExampleSelector instead of examples.\n",
+    "    example_selector=example_selector,\n",
+    "    example_prompt=example_prompt,\n",
+    "    prefix=\"Give the Spanish translation of every input\",\n",
+    "    suffix=\"Input: {sentence}\\nOutput:\", \n",
+    "    input_variables=[\"sentence\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "83fb218a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Give the Spanish translation of every input\n",
+      "\n",
+      "Input: Spot can run.\n",
+      "Output: Spot puede correr.\n",
+      "\n",
+      "Input: See Spot run.\n",
+      "Output: Ver correr a Spot.\n",
+      "\n",
+      "Input: My dog barks.\n",
+      "Output: Mi perro ladra.\n",
+      "\n",
+      "Input: Spot can run fast.\n",
+      "Output:\n"
+     ]
+    }
+   ],
+   "source": [
+    "# An example input with large ngram overlap with \"Spot can run.\"\n",
+    "# and no overlap with \"My dog barks.\"\n",
+    "print(dynamic_prompt.format(sentence=\"Spot can run fast.\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "485f5307",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Give the Spanish translation of every input\n",
+      "\n",
+      "Input: Spot can run.\n",
+      "Output: Spot puede correr.\n",
+      "\n",
+      "Input: See Spot run.\n",
+      "Output: Ver correr a Spot.\n",
+      "\n",
+      "Input: Spot plays fetch.\n",
+      "Output: Spot juega a buscar.\n",
+      "\n",
+      "Input: My dog barks.\n",
+      "Output: Mi perro ladra.\n",
+      "\n",
+      "Input: Spot can run fast.\n",
+      "Output:\n"
+     ]
+    }
+   ],
+   "source": [
+    "# You can add examples to NGramOverlapExampleSelector as well.\n",
+    "new_example = {\"input\": \"Spot plays fetch.\", \"output\": \"Spot juega a buscar.\"}\n",
+    "\n",
+    "example_selector.add_example(new_example)\n",
+    "print(dynamic_prompt.format(sentence=\"Spot can run fast.\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "606ce697",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Give the Spanish translation of every input\n",
+      "\n",
+      "Input: Spot can run.\n",
+      "Output: Spot puede correr.\n",
+      "\n",
+      "Input: See Spot run.\n",
+      "Output: Ver correr a Spot.\n",
+      "\n",
+      "Input: Spot plays fetch.\n",
+      "Output: Spot juega a buscar.\n",
+      "\n",
+      "Input: Spot can run fast.\n",
+      "Output:\n"
+     ]
+    }
+   ],
+   "source": [
+    "# You can set a threshold at which examples are excluded.\n",
+    "# For example, setting threshold equal to 0.0\n",
+    "# excludes examples with no ngram overlaps with input.\n",
+    "# Since \"My dog barks.\" has no ngram overlaps with \"Spot can run fast.\"\n",
+    "# it is excluded.\n",
+    "example_selector.threshold=0.0\n",
+    "print(dynamic_prompt.format(sentence=\"Spot can run fast.\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "id": "7f8d72f7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Give the Spanish translation of every input\n",
+      "\n",
+      "Input: Spot can run.\n",
+      "Output: Spot puede correr.\n",
+      "\n",
+      "Input: Spot plays fetch.\n",
+      "Output: Spot juega a buscar.\n",
+      "\n",
+      "Input: Spot can play fetch.\n",
+      "Output:\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Setting small nonzero threshold\n",
+    "example_selector.threshold=0.09\n",
+    "print(dynamic_prompt.format(sentence=\"Spot can play fetch.\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "id": "09633aa8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Give the Spanish translation of every input\n",
+      "\n",
+      "Input: Spot can play fetch.\n",
+      "Output:\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Setting threshold greater than 1.0\n",
+    "example_selector.threshold=1.0+1e-9\n",
+    "print(dynamic_prompt.format(sentence=\"Spot can play fetch.\"))"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "c746d6f4",
+   "id": "39f30097",
    "metadata": {},
    "outputs": [],
    "source": []