docs[patch]: Adds self query docs, LCEL cheatsheet

deno.json

@@ -22,6 +22,7 @@
     "node-llama-cpp": "npm:/node-llama-cpp",
     "ml-distance": "npm:/ml-distance",
     "pdf-parse": "npm:/pdf-parse",
+    "peggy": "npm:/peggy",
     "readline": "https://deno.land/x/readline@v1.1.0/mod.ts",
     "uuid": "npm:/uuid",
     "youtubei.js": "npm:/youtubei.js",

docs/core_docs/.gitignore

@@ -51,10 +51,10 @@ docs/tutorials/classification.md
 docs/tutorials/classification.mdx
 docs/how_to/tools_prompting.md
 docs/how_to/tools_prompting.mdx
-docs/how_to/tools_as_openai_functions.md
-docs/how_to/tools_as_openai_functions.mdx
-docs/how_to/tools.md
-docs/how_to/tools.mdx
+docs/how_to/tools_builtin.md
+docs/how_to/tools_builtin.mdx
+docs/how_to/tool_calls_multi_modal.md
+docs/how_to/tool_calls_multi_modal.mdx
 docs/how_to/tool_calling.md
 docs/how_to/tool_calling.mdx
 docs/how_to/structured_output.md
@@ -65,6 +65,8 @@ docs/how_to/split_by_token.md
 docs/how_to/split_by_token.mdx
 docs/how_to/sequence.md
 docs/how_to/sequence.mdx
+docs/how_to/self_query.md
+docs/how_to/self_query.mdx
 docs/how_to/recursive_text_splitter.md
 docs/how_to/recursive_text_splitter.mdx
 docs/how_to/query_no_queries.md
@@ -101,6 +103,8 @@ docs/how_to/multiple_queries.md
 docs/how_to/multiple_queries.mdx
 docs/how_to/logprobs.md
 docs/how_to/logprobs.mdx
+docs/how_to/lcel_cheatsheet.md
+docs/how_to/lcel_cheatsheet.mdx
 docs/how_to/graph_semantic.md
 docs/how_to/graph_semantic.mdx
 docs/how_to/graph_prompting.md

docs/core_docs/docs/how_to/agent_executor.ipynb

@@ -16,7 +16,7 @@
     ":::\n",
     "\n",
     "By themselves, language models can't take actions - they just output text.\n",
-    "Agents are systems that use an LLM as a reasoning engineer to determine which actions to take and what the inputs to those actions should be.\n",
+    "Agents are systems that use an LLM as a reasoning engine to determine which actions to take and what the inputs to those actions should be.\n",
     "The results of those actions can then be fed back into the agent and it determine whether more actions are needed, or whether it is okay to finish.\n",
     "\n",
     "In this tutorial we will build an agent that can interact with multiple different tools: one being a local database, the other being a search engine. You will be able to ask this agent questions, watch it call tools, and have conversations with it.\n",

docs/core_docs/docs/how_to/index.mdx

@@ -26,7 +26,9 @@ This highlights functionality that is core to using LangChain.
 
 ## LangChain Expression Language (LCEL)
 
-LangChain Expression Language is a way to create arbitrary custom chains. It is built on the Runnable protocol.
+LangChain Expression Language is a way to create arbitrary custom chains. It is built on the [`Runnable`](https://api.js.langchain.com/classes/langchain_core_runnables.Runnable.html) protocol.
+
+[**LCEL cheatsheet**](/docs/how_to/lcel_cheatsheet/): For a quick overview of how to use the main LCEL primitives.
 
 - [How to: chain runnables](/docs/how_to/sequence)
 - [How to: stream runnables](/docs/how_to/streaming)
@@ -131,6 +133,7 @@ Retrievers are responsible for taking a query and returning relevant documents.
 - [How to: write a custom retriever class](/docs/how_to/custom_retriever)
 - [How to: generate multiple embeddings per document](/docs/how_to/multi_vector)
 - [How to: retrieve the whole document for a chunk](/docs/how_to/parent_document_retriever)
+- [How to: generate metadata filters](/docs/how_to/self_query)
 - [How to: create a time-weighted retriever](/docs/how_to/time_weighted_vectorstore)
 - [How to: reduce retrieval latency](/docs/how_to/reduce_retrieval_latency)