LangSmith and LangChain context var handling evolved in parallel since
originally we didn't expect people to want to interweave the decorator
and langchain code.
Once we get a new langsmith release, this PR will let you seemlessly
hand off between @traceable context and runnable config context so you
can arbitrarily nest code.
It's expected that this fails right now until we get another release of
the SDK
**Description:** Move `FileCallbackHandler` from community to core
**Issue:** #20493
**Dependencies:** None
(imo) `FileCallbackHandler` is a built-in LangChain callback handler
like `StdOutCallbackHandler` and should properly be in in core.
Removes required usage of `requests` from `langchain-core`, all of which
has been deprecated.
- removes Tracer V1 implementations
- removes old `try_load_from_hub` github-based hub implementations
Removal done in a way where imports will still succeed, and usage will
fail with a `RuntimeError`.
This PR completes work for PR #18798 to expose raw tool output in
on_tool_end.
Affected APIs:
* astream_log
* astream_events
* callbacks sent to langsmith via langsmith-sdk
* Any other code that relies on BaseTracer!
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
The root run id (~trace id's) is useful for assigning feedback, but the
current recommended approach is to use callbacks to retrieve it, which
has some drawbacks:
1. Doesn't work for streaming until after the first event
2. Doesn't let you call other endpoints with the same trace ID in
parallel (since you have to wait until the call is completed/started to
use
This PR lets you provide = "run_id" in the runnable config.
Couple considerations:
1. For batch calls, we split the trace up into separate trees (to permit
better rendering). We keep the provided run ID for the first one and
generate a unique one for other elements of the batch.
2. For nested calls, the provided ID is ONLY used on the top root/trace.
### Example Usage
```
chain.invoke("foo", {"run_id": uuid.uuid4()})
```
This PR updates the on_tool_end handlers to return the raw output from the tool instead of casting it to a string.
This is technically a breaking change, though it's impact is expected to be somewhat minimal. It will fix behavior in `astream_events` as well.
Fixes the following issue #18760 raised by @eyurtsev
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
<!-- Thank you for contributing to LangChain!
Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
This PR adds `astream_events` method to Runnables to make it easier to
stream data from arbitrary chains.
* Streaming only works properly in async right now
* One should use `astream()` with if mixing in imperative code as might
be done with tool implementations
* Astream_log has been modified with minimal additive changes, so no
breaking changes are expected
* Underlying callback code / tracing code should be refactored at some
point to handle things more consistently (OK for now)
- ~~[ ] verify event for on_retry~~ does not work until we implement
streaming for retry
- ~~[ ] Any rrenaming? Should we rename "event" to "hook"?~~
- [ ] Any other feedback from community?
- [x] throw NotImplementedError for `RunnableEach` for now
## Example
See this [Example
Notebook](dbbc7fa0d6/docs/docs/modules/agents/how_to/streaming_events.ipynb)
for an example with streaming in the context of an Agent
## Event Hooks Reference
Here is a reference table that shows some events that might be emitted
by the various Runnable objects.
Definitions for some of the Runnable are included after the table.
| event | name | chunk | input | output |
|----------------------|------------------|---------------------------------|-----------------------------------------------|-------------------------------------------------|
| on_chat_model_start | [model name] | | {"messages": [[SystemMessage,
HumanMessage]]} | |
| on_chat_model_stream | [model name] | AIMessageChunk(content="hello")
| | |
| on_chat_model_end | [model name] | | {"messages": [[SystemMessage,
HumanMessage]]} | {"generations": [...], "llm_output": None, ...} |
| on_llm_start | [model name] | | {'input': 'hello'} | |
| on_llm_stream | [model name] | 'Hello' | | |
| on_llm_end | [model name] | | 'Hello human!' |
| on_chain_start | format_docs | | | |
| on_chain_stream | format_docs | "hello world!, goodbye world!" | | |
| on_chain_end | format_docs | | [Document(...)] | "hello world!,
goodbye world!" |
| on_tool_start | some_tool | | {"x": 1, "y": "2"} | |
| on_tool_stream | some_tool | {"x": 1, "y": "2"} | | |
| on_tool_end | some_tool | | | {"x": 1, "y": "2"} |
| on_retriever_start | [retriever name] | | {"query": "hello"} | |
| on_retriever_chunk | [retriever name] | {documents: [...]} | | |
| on_retriever_end | [retriever name] | | {"query": "hello"} |
{documents: [...]} |
| on_prompt_start | [template_name] | | {"question": "hello"} | |
| on_prompt_end | [template_name] | | {"question": "hello"} |
ChatPromptValue(messages: [SystemMessage, ...]) |
Here are declarations associated with the events shown above:
`format_docs`:
```python
def format_docs(docs: List[Document]) -> str:
'''Format the docs.'''
return ", ".join([doc.page_content for doc in docs])
format_docs = RunnableLambda(format_docs)
```
`some_tool`:
```python
@tool
def some_tool(x: int, y: str) -> dict:
'''Some_tool.'''
return {"x": x, "y": y}
```
`prompt`:
```python
template = ChatPromptTemplate.from_messages(
[("system", "You are Cat Agent 007"), ("human", "{question}")]
).with_config({"run_name": "my_template", "tags": ["my_template"]})
```
- Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor
needs manual handling of context vars
<!-- Thank you for contributing to LangChain!
Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
While using `chain.batch`, the default implementation uses a
`ThreadPoolExecutor` and run the chains in separate threads. An issue
with this approach is that that [the token counting
callback](https://python.langchain.com/docs/modules/callbacks/token_counting)
fails to work as a consequence of the context not being propagated
between threads. This PR adds context propagation to the new threads and
adds some thread synchronization in the OpenAI callback. With this
change, the token counting callback works as intended.
Having the context propagation change would be highly beneficial for
those implementing custom callbacks for similar functionalities as well.
---------
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Unnecessarily overridden methods:
- Give the idea the subclass is doing something special (when it isn't)
- Block CTRL-click to the actual method
This PR removes some unnecessarily overridden methods in
`StdOutCallbackHandler`
Supercedes https://github.com/langchain-ai/langchain/pull/12858
Fix some circular deps:
- move PromptValue into top level module bc both PromptTemplates and
OutputParsers import
- move tracer context vars to `tracers.context` and import them in
functions in `callbacks.manager`
- add core import tests
Changes:
- remove langchain_core/schema since no clear distinction b/n schema and
non-schema modules
- make every module that doesn't end in -y plural
- where easy have 1-2 classes per file
- no more than one level of nesting in directories
- only import from top level core modules in langchain
