ChatOpenAI supports a kwarg `stream_options` which can take values
`{"include_usage": True}` and `{"include_usage": False}`.
Setting include_usage to True adds a message chunk to the end of the
stream with usage_metadata populated. In this case the final chunk no
longer includes `"finish_reason"` in the `response_metadata`. This is
the current default and is not yet released. Because this could be
disruptive to workflows, here we remove this default. The default will
now be consistent with OpenAI's API (see parameter
[here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options)).
Examples:
```python
from langchain_openai import ChatOpenAI
llm = ChatOpenAI()
for chunk in llm.stream("hi"):
print(chunk)
```
```
content='' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='Hello' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='!' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
content='' response_metadata={'finish_reason': 'stop'} id='run-8cff4721-2acd-4551-9bf7-1911dae46b92'
```
```python
for chunk in llm.stream("hi", stream_options={"include_usage": True}):
print(chunk)
```
```
content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='Hello' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='!' id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='' response_metadata={'finish_reason': 'stop'} id='run-39ab349b-f954-464d-af6e-72a0927daa27'
content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}
```
```python
llm = ChatOpenAI().bind(stream_options={"include_usage": True})
for chunk in llm.stream("hi"):
print(chunk)
```
```
content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='Hello' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='!' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='' response_metadata={'finish_reason': 'stop'} id='run-59918845-04b2-41a6-8d90-f75fb4506e0d'
content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17}
```
Add kwargs in add_documents function
**langchain**: Add **kwargs in parent_document_retriever"
- **Add kwargs for `add_document` in `parent_document_retriever.py`**
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
**Description:** Update langchainhub integration test dependency and add
an integration test for pulling private prompt
**Dependencies:** langchainhub 0.1.16
Change 'FIREWALL' to 'FIRECRAWL' as I believe this may have been in
error. Other docs refer to 'FIRECRAWL_API_KEY'.
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
- [ ] **Add tests and docs**: 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.
- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
# Description
## Problem
`Runnable.get_graph` fails when `InputType` or `OutputType` property
raises `TypeError`.
-
003c98e5b4/libs/core/langchain_core/runnables/base.py (L250-L274)
-
003c98e5b4/libs/core/langchain_core/runnables/base.py (L394-L396)
This problem prevents getting a graph of `Runnable` objects whose
`InputType` or `OutputType` property raises `TypeError` but whose
`invoke` works well, such as `langchain.output_parsers.RegexParser`,
which I have already pointed out in #19792 that a `TypeError` would
occur.
## Solution
- Add `try-except` syntax to handle `TypeError` to the codes which get
`input_node` and `output_node`.
# Issue
- #19801
# Twitter Handle
- [hmdev3](https://twitter.com/hmdev3)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Thank you for contributing to LangChain!
- [x] **PR title**: community: Add Zep Cloud components + docs +
examples
- [x] **PR message**:
We have recently released our new zep-cloud sdks that are compatible
with Zep Cloud (not Zep Open Source). We have also maintained our Cloud
version of langchain components (ChatMessageHistory, VectorStore) as
part of our sdks. This PRs goal is to port these components to langchain
community repo, and close the gap with the existing Zep Open Source
components already present in community repo (added
ZepCloudMemory,ZepCloudVectorStore,ZepCloudRetriever).
Also added a ZepCloudChatMessageHistory components together with an
expression language example ported from our repo. We have left the
original open source components intact on purpose as to not introduce
any breaking changes.
- **Issue:** -
- **Dependencies:** Added optional dependency of our new cloud sdk
`zep-cloud`
- **Twitter handle:** @paulpaliychuk51
- [x] **Add tests and docs**
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
3 fixes of DuckDB vector store:
- unify defaults in constructor and from_texts (users no longer have to
specify `vector_key`).
- include search similarity into output metadata (fixes#20969)
- significantly improve performance of `from_documents`
Dependencies: added Pandas to speed up `from_documents`.
I was thinking about CSV and JSON options, but I expect trouble loading
JSON values this way and also CSV and JSON options require storing data
to disk.
Anyway, the poetry file for langchain-community already contains a
dependency on Pandas.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
- **Description:** this PR gives clickhouse client the ability to use a
secure connection to the clickhosue server
- **Issue:** fixes#22082
- **Dependencies:** -
- **Twitter handle:** `_codingcoffee_`
Signed-off-by: Ameya Shenoy <shenoy.ameya@gmail.com>
Co-authored-by: Shresth Rana <shresth@grapevine.in>
OpenAI recently added a `stream_options` parameter to its chat
completions API (see [release
notes](https://platform.openai.com/docs/changelog/added-chat-completions-stream-usage)).
When this parameter is set to `{"usage": True}`, an extra "empty"
message is added to the end of a stream containing token usage. Here we
propagate token usage to `AIMessage.usage_metadata`.
We enable this feature by default. Streams would now include an extra
chunk at the end, **after** the chunk with
`response_metadata={'finish_reason': 'stop'}`.
New behavior:
```
[AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='Hello', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='!', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'),
AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde', usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17})]
```
Old behavior (accessible by passing `stream_options={"include_usage":
False}` into (a)stream:
```
[AIMessageChunk(content='', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='Hello', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='!', id='run-1312b971-c5ea-4d92-9015-e6604535f339'),
AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-1312b971-c5ea-4d92-9015-e6604535f339')]
```
From what I can tell this is not yet implemented in Azure, so we enable
only for ChatOpenAI.
Hey, I'm Sasha. The SDK engineer from [Comet](https://comet.com).
This PR updates the CometTracer class.
Added metadata to CometTracerr. From now on, both chains and spans will
send it.
* Lint for usage of standard xml library
* Add forced opt-in for quip client
* Actual security issue is with underlying QuipClient not LangChain
integration (since the client is doing the parsing), but adding
enforcement at the LangChain level.
If tool_use blocks and tool_calls with overlapping IDs are present,
prefer the values of the tool_calls. Allows for mutating AIMessages just
via tool_calls.
```python
class UsageMetadata(TypedDict):
"""Usage metadata for a message, such as token counts.
Attributes:
input_tokens: (int) count of input (or prompt) tokens
output_tokens: (int) count of output (or completion) tokens
total_tokens: (int) total token count
"""
input_tokens: int
output_tokens: int
total_tokens: int
```
```python
class AIMessage(BaseMessage):
...
usage_metadata: Optional[UsageMetadata] = None
"""If provided, token usage information associated with the message."""
...
```
- **Description:** When I was running the sparkllm, I found that the
default parameters currently used could no longer run correctly.
- original parameters & values:
- spark_api_url: "wss://spark-api.xf-yun.com/v3.1/chat"
- spark_llm_domain: "generalv3"
```python
# example
from langchain_community.chat_models import ChatSparkLLM
spark = ChatSparkLLM(spark_app_id="my_app_id",
spark_api_key="my_api_key", spark_api_secret="my_api_secret")
spark.invoke("hello")
```
So I updated them to 3.5 (same as sparkllm official website). After the
update, they can be used normally.
- new parameters & values:
- spark_api_url: "wss://spark-api.xf-yun.com/v3.5/chat"
- spark_llm_domain: "generalv3.5"
This pull request addresses and fixes exception handling in the
UpstageLayoutAnalysisParser and enhances the test coverage by adding
error exception tests for the document loader. These improvements ensure
robust error handling and increase the reliability of the system when
dealing with external API calls and JSON responses.
### Changes Made
1. Fix Request Exception Handling:
- Issue: The existing implementation of UpstageLayoutAnalysisParser did
not properly handle exceptions thrown by the requests library, which
could lead to unhandled exceptions and potential crashes.
- Solution: Added comprehensive exception handling for
requests.RequestException to catch any request-related errors. This
includes logging the error details and raising a ValueError with a
meaningful error message.
2. Add Error Exception Tests for Document Loader:
- New Tests: Introduced new test cases to verify the robustness of the
UpstageLayoutAnalysisLoader against various error scenarios. The tests
ensure that the loader gracefully handles:
- RequestException: Simulates network issues or invalid API requests to
ensure appropriate error handling and user feedback.
- JSONDecodeError: Simulates scenarios where the API response is not a
valid JSON, ensuring the system does not crash and provides clear error
messaging.
**Description:**
- Added propagation of document metadata from O365BaseLoader to
FileSystemBlobLoader (O365BaseLoader uses FileSystemBlobLoader under the
hood).
- This is done by passing dictionary `metadata_dict`: key=filename and
value=dictionary containing document's metadata
- Modified `FileSystemBlobLoader` to accept the `metadata_dict`, use
`mimetype` from it (if available) and pass metadata further into blob
loader.
**Issue:**
- `O365BaseLoader` under the hood downloads documents to temp folder and
then uses `FileSystemBlobLoader` on it.
- However metadata about the document in question is lost in this
process. In particular:
- `mime_type`: `FileSystemBlobLoader` guesses `mime_type` from the file
extension, but that does not work 100% of the time.
- `web_url`: this is useful to keep around since in RAG LLM we might
want to provide link to the source document. In order to work well with
document parsers, we pass the `web_url` as `source` (`web_url` is
ignored by parsers, `source` is preserved)
**Dependencies:**
None
**Twitter handle:**
@martintriska1
Please review @baskaryan
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Thank you for contributing to LangChain!
- [ ] **PR title**: "Add CloudBlobLoader"
- community: Add CloudBlobLoader
- [ ] **PR message**: Add cloud blob loader
- **Description:**
Langchain provides several approaches to read different file formats:
Specific loaders (`CVSLoader`) or blob-compatible loaders
(`FileSystemBlobLoader`). The only implementation proposed for
BlobLoader is `FileSystemBlobLoader`.
Many projects retrieve files from cloud storage. We propose a new
implementation of `BlobLoader` to read files from the three cloud
storage systems. The interface is strictly identical to
`FileSystemBlobLoader`. The only difference is the constructor, which
takes a cloud "url" object such as `s3://my-bucket`, `az://my-bucket`,
or `gs://my-bucket`.
By streamlining the process, this novel implementation eliminates the
requirement to pre-download files from cloud storage to local temporary
files (which are seldom removed).
The code relies on the
[CloudPathLib](https://cloudpathlib.drivendata.org/stable/) library to
interpret cloud URLs. This has been added as an optional dependency.
```Python
loader = CloudBlobLoader("s3://mybucket/id")
for blob in loader.yield_blobs():
print(blob)
```
- [X] **Dependencies:** CloudPathLib
- [X] **Twitter handle:** pprados
- [X] **Add tests and docs**: Add unit test, but it's easy to convert to
integration test, with some files in a cloud storage (see
`test_cloud_blob_loader.py`)
- [X] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified.
Hello from Paris @hwchase17. Can you review this PR?
---------
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
This PR contains 4 added functions:
- max_marginal_relevance_search_by_vector
- amax_marginal_relevance_search_by_vector
- max_marginal_relevance_search
- amax_marginal_relevance_search
I'm no langchain expert, but tried do inspect other vectorstore sources
like chroma, to build these functions for SurrealDB. If someone has some
changes for me, please let me know. Otherwise I would be happy, if these
changes are added to the repository, so that I can use the orignal repo
and not my local monkey patched version.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
