The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
community: update perplexity documentation (#30450)
David Sánchez Sánchezd7b13e12ee82
diff --git a/docs/docs/integrations/chat/perplexity.ipynb b/docs/docs/integrations/chat/perplexity.ipynbindex b2545aad14..2a9c0efce0 100644--- a/docs/docs/integrations/chat/perplexity.ipynb+++ b/docs/docs/integrations/chat/perplexity.ipynb@@ -173,6 +173,41 @@"response.content"]},+ {+ "cell_type": "markdown",+ "id": "a7f8f61b",+ "metadata": {},+ "source": [+ "## Using Perplexity-specific parameters through `ChatPerplexity`\n",+ "\n",+ "You can also use Perplexity-specific parameters through the ChatPerplexity class. For example, parameters like search_domain_filter, return_images, return_related_questions or search_recency_filter using the extra_body parameter as shown below:"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "id": "73960f51",+ "metadata": {},+ "outputs": [+ {+ "data": {+ "text/plain": [+ "\"Sure, here's a cat joke for you:\\n\\nWhy are cats bad storytellers?\\n\\nBecause they only have one tale. (Pun alert!)\\n\\nSource: OneLineFun.com [4]\""+ ]+ },+ "execution_count": 11,+ "metadata": {},+ "output_type": "execute_result"+ }+ ],+ "source": [+ "chat = ChatPerplexity(temperature=0.7, model=\"llama-3.1-sonar-small-128k-online\")\n",+ "response = chat.invoke(\n",+ " \"Tell me a joke about cats\", extra_body={\"search_recency_filter\": \"week\"}\n",+ ")\n",+ "response.content"+ ]+ },{"cell_type": "markdown","id": "13d93dc4",@@ -216,13 +251,56 @@],"source": ["chat = ChatPerplexity(temperature=0.7, model=\"llama-3.1-sonar-small-128k-online\")\n",- "prompt = ChatPromptTemplate.from_messages(\n",- " [(\"human\", \"Give me a list of famous tourist attractions in Pakistan\")]\n",- ")\n",- "chain = prompt | chat\n",- "for chunk in chain.stream({}):\n",+ "\n",+ "for chunk in chat.stream(\"Give me a list of famous tourist attractions in Pakistan\"):\n"," print(chunk.content, end=\"\", flush=True)"]+ },+ {+ "cell_type": "markdown",+ "id": "397c43de",+ "metadata": {},+ "source": [+ "## `ChatPerplexity` Supports Structured Outputs for Tier 3+ Users"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": 6,+ "id": "1bae9b80-394a-4340-9c30-612c136b742a",+ "metadata": {},+ "outputs": [+ {+ "data": {+ "text/plain": [+ "AnswerFormat(first_name='Michael', last_name='Jordan', year_of_birth=1963, num_seasons_in_nba=15)"+ ]+ },+ "execution_count": 6,+ "metadata": {},+ "output_type": "execute_result"+ }+ ],+ "source": [+ "from pydantic import BaseModel\n",+ "\n",+ "\n",+ "class AnswerFormat(BaseModel):\n",+ " first_name: str\n",+ " last_name: str\n",+ " year_of_birth: int\n",+ " num_seasons_in_nba: int\n",+ "\n",+ "\n",+ "chat = ChatPerplexity(temperature=0.7, model=\"sonar-pro\")\n",+ "structured_chat = chat.with_structured_output(AnswerFormat)\n",+ "response = structured_chat.invoke(\n",+ " \"Tell me about Michael Jordan. Return your answer \"\n",+ " \"as JSON with keys first_name (str), last_name (str), \"\n",+ " \"year_of_birth (int), and num_seasons_in_nba (int).\"\n",+ ")\n",+ "response"+ ]}],"metadata": {@@ -241,7 +319,7 @@"name": "python","nbconvert_exporter": "python","pygments_lexer": "ipython3",- "version": "3.10.12"+ "version": "3.10.4"}},"nbformat": 4,