Merge branch 'master' into eugene/foo_foo

docs/docs/concepts/structured_outputs.mdx

@@ -66,7 +66,7 @@ Several more powerful methods that utilizes native features in the model provide
 
 Many [model providers support](/docs/integrations/chat/) tool calling, a concept discussed in more detail in our [tool calling guide](/docs/concepts/tool_calling/).
 In short, tool calling involves binding a tool to a model and, when appropriate, the model can *decide* to call this tool and ensure its response conforms to the tool's schema.
-With this in mind, the central concept is strightforward: *simply bind our schema to a model as a tool!*
+With this in mind, the central concept is straightforward: *simply bind our schema to a model as a tool!*
 Here is an example using the `ResponseFormatter` schema defined above:
 
 ```python
@@ -106,7 +106,7 @@ ai_msg.content
 ```
 
 One important point to flag: the model *still* returns a string, which needs to be parsed into a JSON object.
-This can, of course, simply use the `json` library or a JSON output parser if you need more adavanced functionality.
+This can, of course, simply use the `json` library or a JSON output parser if you need more advanced functionality.
 See this [how-to guide on the JSON output parser](/docs/how_to/output_parser_json) for more details.
 
 ```python
@@ -117,7 +117,7 @@ json_object = json.loads(ai_msg.content)
 
 ## Structured output method 
 
-There a few challenges when producing structured output with the above methods: 
+There are a few challenges when producing structured output with the above methods: 
 
 (1) If using tool calling, tool call arguments needs to be parsed from a dictionary back to the original schema.  
 
@@ -145,4 +145,4 @@ ResponseFormatter(answer="The powerhouse of the cell is the mitochondrion. Mitoc
 
 For more details on usage, see our [how-to guide](/docs/how_to/structured_output/#the-with_structured_output-method).
 
-:::
+:::

docs/docs/how_to/agent_executor.ipynb

@@ -35,7 +35,7 @@
     "- Creating a [Retriever](/docs/concepts/retrievers) to expose specific information to our agent\n",
     "- Using a Search [Tool](/docs/concepts/tools) to look up things online\n",
     "- [`Chat History`](/docs/concepts/chat_history), which allows a chatbot to \"remember\" past interactions and take them into account when responding to follow-up questions. \n",
-    "- Debugging and tracing your application using [LangSmith](/docs/concepts/#langsmith)\n",
+    "- Debugging and tracing your application using [LangSmith](https://docs.smith.langchain.com/)\n",
     "\n",
     "## Setup\n",
     "\n",

docs/docs/how_to/example_selectors_langsmith.ipynb

@@ -13,7 +13,7 @@
     "<Prerequisites titlesAndLinks={[\n",
     "  [\"Chat models\", \"/docs/concepts/chat_models\"],\n",
     "  [\"Few-shot-prompting\", \"/docs/concepts/few-shot-prompting\"],\n",
-    "  [\"LangSmith\", \"/docs/concepts/#langsmith\"],\n",
+    "  [\"LangSmith\", \"https://docs.smith.langchain.com/\"],\n",
     "]} />\n",
     "\n",
     "\n",

docs/docs/how_to/few_shot_examples.ipynb

@@ -23,7 +23,7 @@
     "- [Prompt templates](/docs/concepts/prompt_templates)\n",
     "- [Example selectors](/docs/concepts/example_selectors)\n",
     "- [LLMs](/docs/concepts/text_llms)\n",
-    "- [Vectorstores](/docs/concepts/#vector-stores)\n",
+    "- [Vectorstores](/docs/concepts/vectorstores)\n",
     "\n",
     ":::\n",
     "\n",

docs/docs/how_to/few_shot_examples_chat.ipynb

@@ -23,7 +23,7 @@
     "- [Prompt templates](/docs/concepts/prompt_templates)\n",
     "- [Example selectors](/docs/concepts/example_selectors)\n",
     "- [Chat models](/docs/concepts/chat_models)\n",
-    "- [Vectorstores](/docs/concepts/#vector-stores)\n",
+    "- [Vectorstores](/docs/concepts/vectorstores)\n",
     "\n",
     ":::\n",
     "\n",

docs/docs/how_to/index.mdx

@@ -159,7 +159,7 @@ What LangChain calls [LLMs](/docs/concepts/text_llms) are older forms of languag
 
 ### Vector stores
 
-[Vector stores](/docs/concepts/#vector-stores) are databases that can efficiently store and retrieve embeddings.
+[Vector stores](/docs/concepts/vectorstores) are databases that can efficiently store and retrieve embeddings.
 
 - [How to: use a vector store to retrieve data](/docs/how_to/vectorstores)
 

docs/docs/how_to/output_parser_structured.ipynb

@@ -214,7 +214,7 @@
    "id": "3ca23082-c602-4ee8-af8c-a185b1f42bd1",
    "metadata": {},
    "source": [
-    "While the PydanticOutputParser cannot:"
+    "While the `PydanticOutputParser` cannot:"
    ]
   },
   {

docs/docs/how_to/output_parser_xml.ipynb

@@ -18,7 +18,7 @@
     "\n",
     ":::\n",
     "\n",
-    "LLMs from different providers often have different strengths depending on the specific data they are trianed on. This also means that some may be \"better\" and more reliable at generating output in formats other than JSON.\n",
+    "LLMs from different providers often have different strengths depending on the specific data they are trained on. This also means that some may be \"better\" and more reliable at generating output in formats other than JSON.\n",
     "\n",
     "This guide shows you how to use the [`XMLOutputParser`](https://python.langchain.com/api_reference/core/output_parsers/langchain_core.output_parsers.xml.XMLOutputParser.html) to prompt models for XML output, then and parse that output into a usable format.\n",
     "\n",

docs/docs/how_to/output_parser_yaml.ipynb

@@ -18,7 +18,7 @@
     "\n",
     ":::\n",
     "\n",
-    "LLMs from different providers often have different strengths depending on the specific data they are trianed on. This also means that some may be \"better\" and more reliable at generating output in formats other than JSON.\n",
+    "LLMs from different providers often have different strengths depending on the specific data they are trained on. This also means that some may be \"better\" and more reliable at generating output in formats other than JSON.\n",
     "\n",
     "This output parser allows users to specify an arbitrary schema and query LLMs for outputs that conform to that schema, using YAML to format their response.\n",
     "\n",

docs/docs/how_to/passthrough.ipynb

@@ -153,7 +153,7 @@
     "\n",
     "## Next steps\n",
     "\n",
-    "Now you've learned how to pass data through your chains to help to help format the data flowing through your chains.\n",
+    "Now you've learned how to pass data through your chains to help format the data flowing through your chains.\n",
     "\n",
     "To learn more, see the other how-to guides on runnables in this section."
    ]

docs/docs/integrations/retrievers/index.mdx

@@ -16,7 +16,7 @@ Retrievers accept a string query as input and return a list of [Documents](https
 
 For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
 
-Note that all [vector stores](/docs/concepts/#vector-stores) can be [cast to retrievers](/docs/how_to/vectorstore_retriever/).
+Note that all [vector stores](/docs/concepts/vectorstores) can be [cast to retrievers](/docs/how_to/vectorstore_retriever/).
 Refer to the vector store [integration docs](/docs/integrations/vectorstores/) for available vector stores.
 This page lists custom retrievers, implemented via subclassing [BaseRetriever](/docs/how_to/custom_retriever/).
 

docs/docs/integrations/vectorstores/index.mdx

@@ -7,7 +7,7 @@ sidebar_class_name: hidden
 
 import { CategoryTable, IndexTable } from "@theme/FeatureTables";
 
-A [vector store](/docs/concepts/#vector-stores) stores [embedded](/docs/concepts/embedding_models) data and performs similarity search.
+A [vector store](/docs/concepts/vectorstores) stores [embedded](/docs/concepts/embedding_models) data and performs similarity search.
 
 <CategoryTable category="vectorstores" />
 

docs/docs/tutorials/llm_chain.ipynb

@@ -27,7 +27,7 @@
     "\n",
     "- Using [LangChain Expression Language (LCEL)](/docs/concepts/lcel) to chain components together\n",
     "\n",
-    "- Debugging and tracing your application using [LangSmith](/docs/concepts/#langsmith)\n",
+    "- Debugging and tracing your application using [LangSmith](https://docs.smith.langchain.com/)\n",
     "\n",
     "- Deploying your application with [LangServe](/docs/concepts/#langserve)\n",
     "\n",

docs/docs/tutorials/local_rag.ipynb

@@ -14,7 +14,7 @@
     "- [Chat Models](/docs/concepts/chat_models)\n",
     "- [Chaining runnables](/docs/how_to/sequence/)\n",
     "- [Embeddings](/docs/concepts/embedding_models)\n",
-    "- [Vector stores](/docs/concepts/#vector-stores)\n",
+    "- [Vector stores](/docs/concepts/vectorstores)\n",
     "- [Retrieval-augmented generation](/docs/tutorials/rag/)\n",
     "\n",
     ":::\n",

docs/docs/tutorials/pdf_qa.ipynb

@@ -26,7 +26,7 @@
     "- [Document loaders](/docs/concepts/document_loaders)\n",
     "- [Chat models](/docs/concepts/chat_models)\n",
     "- [Embeddings](/docs/concepts/embedding_models)\n",
-    "- [Vector stores](/docs/concepts/#vector-stores)\n",
+    "- [Vector stores](/docs/concepts/vectorstores)\n",
     "- [Retrieval-augmented generation](/docs/tutorials/rag/)\n",
     "\n",
     ":::\n",
@@ -117,7 +117,7 @@
     "\n",
     "## Question answering with RAG\n",
     "\n",
-    "Next, you'll prepare the loaded documents for later retrieval. Using a [text splitter](/docs/concepts/text_splitters), you'll split your loaded documents into smaller documents that can more easily fit into an LLM's context window, then load them into a [vector store](/docs/concepts/#vector-stores). You can then create a [retriever](/docs/concepts/retrievers) from the vector store for use in our RAG chain:\n",
+    "Next, you'll prepare the loaded documents for later retrieval. Using a [text splitter](/docs/concepts/text_splitters), you'll split your loaded documents into smaller documents that can more easily fit into an LLM's context window, then load them into a [vector store](/docs/concepts/vectorstores). You can then create a [retriever](/docs/concepts/retrievers) from the vector store for use in our RAG chain:\n",
     "\n",
     "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
     "\n",

docs/docs/tutorials/qa_chat_history.ipynb

@@ -24,7 +24,7 @@
     "- [Chat history](/docs/concepts/chat_history)\n",
     "- [Chat models](/docs/concepts/chat_models)\n",
     "- [Embeddings](/docs/concepts/embedding_models)\n",
-    "- [Vector stores](/docs/concepts/#vector-stores)\n",
+    "- [Vector stores](/docs/concepts/vectorstores)\n",
     "- [Retrieval-augmented generation](/docs/tutorials/rag/)\n",
     "- [Tools](/docs/concepts/tools)\n",
     "- [Agents](/docs/concepts/agents)\n",

docs/docs/tutorials/query_analysis.ipynb

@@ -24,7 +24,7 @@
     "- [Document loaders](/docs/concepts/document_loaders)\n",
     "- [Chat models](/docs/concepts/chat_models)\n",
     "- [Embeddings](/docs/concepts/embedding_models)\n",
-    "- [Vector stores](/docs/concepts/#vector-stores)\n",
+    "- [Vector stores](/docs/concepts/vectorstores)\n",
     "- [Retrieval](/docs/concepts/retrieval)\n",
     "\n",
     ":::\n",

docs/docs/tutorials/rag.ipynb

@@ -41,7 +41,7 @@
     "### Indexing\n",
     "1. **Load**: First we need to load our data. This is done with [Document Loaders](/docs/concepts/document_loaders).\n",
     "2. **Split**: [Text splitters](/docs/concepts/text_splitters) break large `Documents` into smaller chunks. This is useful both for indexing data and for passing it in to a model, since large chunks are harder to search over and won't fit in a model's finite context window.\n",
-    "3. **Store**: We need somewhere to store and index our splits, so that they can later be searched over. This is often done using a [VectorStore](/docs/concepts/#vector-stores) and [Embeddings](/docs/concepts/embedding_models) model.\n",
+    "3. **Store**: We need somewhere to store and index our splits, so that they can later be searched over. This is often done using a [VectorStore](/docs/concepts/vectorstores) and [Embeddings](/docs/concepts/embedding_models) model.\n",
     "\n",
     "![index_diagram](../../static/img/rag_indexing.png)\n",
     "\n",

docs/scripts/append_related_links.py

@@ -3,47 +3,59 @@ import multiprocessing
 import re
 import sys
 from pathlib import Path
+from typing import Optional
 
+# List of 4-tuples (integration_name, display_name, concept_page, how_to_fragment)
+INTEGRATION_INFO = [
+    ("chat", "Chat model", "chat_models", "chat-models"),
+    ("llms", "LLM", "text_llms", "llms"),
+    ("text_embedding", "Embedding model", "embedding_models", "embedding-models"),
+    ("document_loaders", "Document loader", "document_loaders", "document-loaders"),
+    ("vectorstores", "Vector store", "vectorstores", "vector-stores"),
+    ("retrievers", "Retriever", "retrievers", "retrievers"),
+    ("tools", "Tool", "tools", "tools"),
+    # stores is a special case because there are no key-value store how-tos yet
+    # this is a placeholder for when we do have them
+    # for now the related links section will only contain the conceptual guide.
+    ("stores", "Key-value store", "key_value_stores", "key-value-stores"),
+]
 
-def _generate_related_links_section(integration_type: str, notebook_name: str):
-    concept_display_name = None
-    concept_heading = None
-    if integration_type == "chat":
-        concept_display_name = "Chat model"
-        concept_heading = "chat-models"
-    elif integration_type == "llms":
-        concept_display_name = "LLM"
-        concept_heading = "llms"
-    elif integration_type == "text_embedding":
-        concept_display_name = "Embedding model"
-        concept_heading = "embedding-models"
-    elif integration_type == "document_loaders":
-        concept_display_name = "Document loader"
-        concept_heading = "document-loaders"
-    elif integration_type == "vectorstores":
-        concept_display_name = "Vector store"
-        concept_heading = "vector-stores"
-    elif integration_type == "retrievers":
-        concept_display_name = "Retriever"
-        concept_heading = "retrievers"
-    elif integration_type == "tools":
-        concept_display_name = "Tool"
-        concept_heading = "tools"
-    elif integration_type == "stores":
-        concept_display_name = "Key-value store"
-        concept_heading = "key-value-stores"
-        # Special case because there are no key-value store how-tos yet
-        return f"""## Related
+# Create a dictionary with key being the first element (integration_name) and value being the rest of the tuple
+INTEGRATION_INFO_DICT = {
+    integration_name: rest for integration_name, *rest in INTEGRATION_INFO
+}
 
-- [{concept_display_name} conceptual guide](/docs/concepts/#{concept_heading})
+RELATED_LINKS_SECTION = """## Related
+- {concept_display_name} [conceptual guide](/docs/concepts/{concept_page})
+- {concept_display_name} [how-to guides](/docs/how_to/#{how_to_fragment})
 """
-    else:
+
+RELATED_LINKS_WITHOUT_HOW_TO_SECTION = """## Related
+- {concept_display_name} [conceptual guide](/docs/concepts/{concept_page})
+"""
+
+
+def _generate_related_links_section(
+    integration_type: str, notebook_name: str
+) -> Optional[str]:
+    if integration_type not in INTEGRATION_INFO_DICT:
         return None
-    return f"""## Related
+    concept_display_name, concept_page, how_to_fragment = INTEGRATION_INFO_DICT[
+        integration_type
+    ]
 
-- {concept_display_name} [conceptual guide](/docs/concepts/#{concept_heading})
-- {concept_display_name} [how-to guides](/docs/how_to/#{concept_heading})
-"""
+    # Special case because there are no key-value store how-tos yet
+    if integration_type == "stores":
+        return RELATED_LINKS_WITHOUT_HOW_TO_SECTION.format(
+            concept_display_name=concept_display_name,
+            concept_page=concept_page,
+        )
+
+    return RELATED_LINKS_SECTION.format(
+        concept_display_name=concept_display_name,
+        concept_page=concept_page,
+        how_to_fragment=how_to_fragment,
+    )
 
 
 def _process_path(doc_path: Path):