docs: mdx v3 compat [wip]

This commit is contained in:
Erick Friis
2024-09-12 21:22:48 -07:00
parent 608c4a4327
commit c858c6cc09
10 changed files with 125 additions and 15 deletions

View File

@@ -452,7 +452,7 @@ the effectiveness of the proposed technique, we implemented a ToT-based solver
for the Sudoku Puzzle. Experimental results show that the ToT framework can
significantly increase the success rate of Sudoku puzzle solving. Our
implementation of the ToT-based Sudoku solver is available on GitHub:
\url{https://github.com/jieyilong/tree-of-thought-puzzle-solver}.
\url\{https://github.com/jieyilong/tree-of-thought-puzzle-solver\}.
## Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

View File

@@ -734,10 +734,10 @@ of the object.
If you're creating a custom chain or runnable, you need to remember to propagate request time
callbacks to any child objects.
:::important Async in Python<=3.10
:::important Async in Python&lt;=3.10
Any `RunnableLambda`, a `RunnableGenerator`, or `Tool` that invokes other runnables
and is running `async` in python<=3.10, will have to propagate callbacks to child
and is running `async` in python&lt;=3.10, will have to propagate callbacks to child
objects manually. This is because LangChain cannot automatically propagate
callbacks to child objects in this case.

View File

@@ -23,7 +23,7 @@
"\n",
":::{.callout-danger}\n",
"\n",
"If you're on `python<=3.10`, you need to remember to propagate `config` or `callbacks` when invoking other `runnable` from within a `RunnableLambda`, `RunnableGenerator` or `@tool`. If you do not do this,\n",
"If you're on `python&lt;=3.10`, you need to remember to propagate `config` or `callbacks` when invoking other `runnable` from within a `RunnableLambda`, `RunnableGenerator` or `@tool`. If you do not do this,\n",
"the callbacks will not be propagated to the child runnables being invoked.\n",
":::"
]

View File

@@ -38,9 +38,9 @@
"\n",
"\n",
":::caution COMPATIBILITY\n",
"LangChain cannot automatically propagate configuration, including callbacks necessary for astream_events(), to child runnables if you are running async code in python<=3.10. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
"LangChain cannot automatically propagate configuration, including callbacks necessary for astream_events(), to child runnables if you are running async code in python&lt;=3.10. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
"\n",
"If you are running python<=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
"If you are running python&lt;=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
"\n",
"If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in other Python versions.\n",
":::"
@@ -115,7 +115,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"In python <= 3.10, you must propagate the config manually!"
"In python &lt;= 3.10, you must propagate the config manually!"
]
},
{
@@ -147,7 +147,7 @@
"async def bar(x: str, config: RunnableConfig) -> str:\n",
" \"\"\"An example that shows how to manually propagate config.\n",
"\n",
" You must do this if you're running python<=3.10.\n",
" You must do this if you're running python&lt;=t;=3.10.\n",
" \"\"\"\n",
" await adispatch_custom_event(\"event1\", {\"x\": x}, config=config)\n",
" await adispatch_custom_event(\"event2\", 5, config=config)\n",
@@ -223,7 +223,7 @@
"async def bar(x: str, config: RunnableConfig) -> str:\n",
" \"\"\"An example that shows how to manually propagate config.\n",
"\n",
" You must do this if you're running python<=3.10.\n",
" You must do this if you're running python&lt;=t;=3.10.\n",
" \"\"\"\n",
" await adispatch_custom_event(\"event1\", {\"x\": x}, config=config)\n",
" await adispatch_custom_event(\"event2\", 5, config=config)\n",

View File

@@ -39,7 +39,7 @@
"| `AIMessageChunk` / `HumanMessageChunk` / ... | Chunk variant of each type of message. |\n",
"\n",
"\n",
"::: {.callout-note}\n",
":::note\n",
"`ToolMessage` and `FunctionMessage` closely follow OpenAI's `function` and `tool` roles.\n",
"\n",
"This is a rapidly developing field and as more models add function calling capabilities. Expect that there will be additions to this schema.\n",
@@ -145,7 +145,7 @@
"| `_astream` | Use to implement async version of `_stream`. | Optional |\n",
"\n",
"\n",
":::{.callout-tip}\n",
":::tip\n",
"The `_astream` implementation uses `run_in_executor` to launch the sync `_stream` in a separate thread if `_stream` is implemented, otherwise it fallsback to use `_agenerate`.\n",
"\n",
"You can use this trick if you want to reuse the `_stream` implementation, but if you're able to implement code that's natively async that's a better solution since that code will run with less overhead.\n",

View File

@@ -22,7 +22,7 @@
"\n",
"LangChain cannot automatically propagate configuration, including callbacks necessary for `astream_events()`, to child runnables if you are running `async` code in `python<=3.10`. This is a common reason why you may fail to see events being emitted from custom runnables or tools.\n",
"\n",
"If you are running python<=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
"If you are running python&lt;=3.10, you will need to manually propagate the `RunnableConfig` object to the child runnable in async environments. For an example of how to manually propagate the config, see the implementation of the `bar` RunnableLambda below.\n",
"\n",
"If you are running python>=3.11, the `RunnableConfig` will automatically propagate to child runnables in async environment. However, it is still a good idea to propagate the `RunnableConfig` manually if your code may run in older Python versions.\n",
"\n",

View File

@@ -474,7 +474,7 @@
"# Other Notes\n",
">* More documentation can be found at [LangChain-MongoDB](https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/langchain/) site\n",
">* This feature is Generally Available and ready for production deployments.\n",
">* The langchain version 0.0.305 ([release notes](https://github.com/langchain-ai/langchain/releases/tag/v0.0.305)) introduces the support for $vectorSearch MQL stage, which is available with MongoDB Atlas 6.0.11 and 7.0.2. Users utilizing earlier versions of MongoDB Atlas need to pin their LangChain version to <=0.0.304\n",
">* The langchain version 0.0.305 ([release notes](https://github.com/langchain-ai/langchain/releases/tag/v0.0.305)) introduces the support for $vectorSearch MQL stage, which is available with MongoDB Atlas 6.0.11 and 7.0.2. Users utilizing earlier versions of MongoDB Atlas need to pin their LangChain version to &lt;=0.0.304\n",
"> "
]
},

View File

@@ -255,7 +255,7 @@
"| \\$eq | Equality (==) |\n",
"| \\$ne | Inequality (!=) |\n",
"| \\$lt | Less than (<) |\n",
"| \\$lte | Less than or equal (<=) |\n",
"| \\$lte | Less than or equal (&lt;=) |\n",
"| \\$gt | Greater than (>) |\n",
"| \\$gte | Greater than or equal (>=) |\n",
"| \\$in | Special Cased (in) |\n",

View File

@@ -372,7 +372,7 @@
"| `$eq` | Equality (==) |\n",
"| `$ne` | Inequality (!=) |\n",
"| `$lt` | Less than (<) |\n",
"| `$lte` | Less than or equal (<=) |\n",
"| `$lte` | Less than or equal (&lt;=) |\n",
"| `$gt` | Greater than (>) |\n",
"| `$gte` | Greater than or equal (>=) |\n",
"| `$in` | Contained in a set of given values (in) |\n",

110
docs/it.md Normal file
View File

@@ -0,0 +1,110 @@
[ERROR] 36/1326 MDX files couldn't compile!
---
Error while compiling file docs/additional_resources/arxiv_references.mdx:455:11
Details: Could not parse expression with acorn
---
Error while compiling file docs/how_to/custom_chat_model.md:38:6
Details: Could not parse expression with acorn
---
Error while compiling file docs/how_to/extraction_parse.md:88:9
Details: Could not parse expression with acorn
---
Error while compiling file docs/how_to/parallel.md:75:6
Details: Could not parse expression with acorn
---
Error while compiling file docs/how_to/self_query.md:254:2
Details: Unexpected character `<` (U+003C) before name, expected a character that can start a name, such as a letter, `$`, or `_`
---
Error while compiling file docs/how_to/sql_csv.md
Details: These MDX global variables do not seem to be available in scope: df
---
Error while compiling file docs/how_to/streaming.md:428:90
Details: Could not parse expression with acorn
---
Error while compiling file docs/how_to/structured_output.md:510:15
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/chat/anthropic_functions.md:7:6
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/document_loaders/blockchain.md:27:21
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/document_loaders/confluence.md:19:1
Details: Expected a closing tag for `<page_id>` (19:149-19:158) before the end of `paragraph`
---
Error while compiling file docs/integrations/document_loaders/figma.md
Details: These MDX global variables do not seem to be available in scope: node_id
---
Error while compiling file docs/integrations/document_loaders/mintbase.md:27:21
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/document_loaders/mongodb.md:23:23
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/document_loaders/rspace.md:20:5
Details: Expected a closing tag for `<YOUR_KEY>` (20:20-20:30) before the end of `paragraph`
---
Error while compiling file docs/integrations/document_loaders/slack.md
Details: These MDX global variables do not seem to be available in scope: your_slack_domain
---
Error while compiling file docs/integrations/document_loaders/web_base.md:54:35
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/llms/runhouse.md:151:109
Details: Unexpected character `2` (U+0032) before name, expected a character that can start a name, such as a letter, `$`, or `_`
---
Error while compiling file docs/integrations/providers/dspy.md
Details: These MDX global variables do not seem to be available in scope: context question
---
Error while compiling file docs/integrations/providers/figma.mdx
Details: These MDX global variables do not seem to be available in scope: node_id
---
Error while compiling file docs/integrations/providers/xinference.mdx
Details: These MDX global variables do not seem to be available in scope: supervisor_host
---
Error while compiling file docs/integrations/tools/amadeus.md:146:11
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/tools/azure_ai_services.md:102:11
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/tools/azure_cognitive_services.md:102:11
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/tools/bash.md:68:11
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/tools/eleven_labs_tts.md:87:11
Details: Could not parse expression with acorn
---
Error while compiling file /docs/docs/integrations/tools/github.md
Details: These MDX global variables do not seem to be available in scope: name repo username
---
Error while compiling file docs/integrations/tools/gitlab.md
Details: These MDX global variables do not seem to be available in scope: name repo username
---
Error while compiling file docs/integrations/tools/ifttt.md
Details: These MDX global variables do not seem to be available in scope: JsonPayload
---
Error while compiling file docs/integrations/tools/lemonai.md:65:138
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/tools/playwright.md:174:11
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/vectorstores/activeloop_deeplake.md:305:122
Details: Could not parse expression with acorn
---
Error while compiling file docs/integrations/vectorstores/alibabacloud_opensearch.md:190:87
Details: Unexpected character `@` (U+0040) in member name, expected a name character such as letters, digits, `$`, or `_`; whitespace before attributes; or the end of the tag (note: to create a link in MDX, use `[text](url)`)
---
Error while compiling file docs/integrations/vectorstores/baiducloud_vector_search.md:79:38
Details: Unexpected character `@` (U+0040) in name, expected a name character such as letters, digits, `$`, or `_`; whitespace before attributes; or the end of the tag (note: to create a link in MDX, use `[text](url)`)
---
Error while compiling file docs/integrations/vectorstores/pgvector.md:155:27
Details: Unexpected character `)` (U+0029) before name, expected a character that can start a name, such as a letter, `$`, or `_`
---
Error while compiling file docs/integrations/vectorstores/sap_hanavector.md:199:26
Details: Unexpected character `)` (U+0029) before name, expected a character that can start a name, such as a letter, `$`, or `_`
---