Commit Graph

340 Commits (f8a54d1d731a816897d3b4b0a0f814a099231580)

Author SHA1 Message Date
killind-dev f8a54d1d73
chroma: Add chroma partner package (#19292)
**Description:** Adds chroma to the partners package. Tests & code
mirror those in the community package.
**Dependencies:** None
**Twitter handle:** @akiradev0x

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
5 months ago
Yuki Oshima 12190ad728
openai[patch]: Fix langchain-openai unknown parameter error with gpt-4-turbo (#20271)
**Description:** 

I fixed langchain-openai unknown parameter error with gpt-4-turbo.

It seems that the behavior of the Chat Completions API implicitly
changed when using the latest gpt-4-turbo model, differing from previous
models. It now appears to reject parameters that are not listed in the
[API
Reference](https://platform.openai.com/docs/api-reference/chat/create).
So I found some errors and fixed them.

**Issue:** https://github.com/langchain-ai/langchain/issues/20264

**Dependencies:** none

**Twitter handle:** https://twitter.com/oshima_123
5 months ago
Erick Friis 9eb6f538f0
infra, multiple: rc release versions (#20252) 5 months ago
Bagatur 0d0458d1a7
mistralai[patch]: Pre-release 0.1.2-rc.1 (#20251) 5 months ago
Bagatur e4046939d0
anthropic[patch]: Pre-release 0.1.8-rc.1 (#20250) 5 months ago
Bagatur a8eb0f5b1b
openai[patch]: pre-release 0.1.3-rc.1 (#20249) 5 months ago
Bagatur 9514bc4d67
core[minor], ...: add tool calls message (#18947)
core[minor], langchain[patch], openai[minor], anthropic[minor], fireworks[minor], groq[minor], mistralai[minor]

```python
class ToolCall(TypedDict):
    name: str
    args: Dict[str, Any]
    id: Optional[str]

class InvalidToolCall(TypedDict):
    name: Optional[str]
    args: Optional[str]
    id: Optional[str]
    error: Optional[str]

class ToolCallChunk(TypedDict):
    name: Optional[str]
    args: Optional[str]
    id: Optional[str]
    index: Optional[int]


class AIMessage(BaseMessage):
    ...
    tool_calls: List[ToolCall] = []
    invalid_tool_calls: List[InvalidToolCall] = []
    ...


class AIMessageChunk(AIMessage, BaseMessageChunk):
    ...
    tool_call_chunks: Optional[List[ToolCallChunk]] = None
    ...
```
Important considerations:
- Parsing logic occurs within different providers;
- ~Changing output type is a breaking change for anyone doing explicit
type checking;~
- ~Langsmith rendering will need to be updated:
https://github.com/langchain-ai/langchainplus/pull/3561~
- ~Langserve will need to be updated~
- Adding chunks:
- ~AIMessage + ToolCallsMessage = ToolCallsMessage if either has
non-null .tool_calls.~
- Tool call chunks are appended, merging when having equal values of
`index`.
  - additional_kwargs accumulate the normal way.
- During streaming:
- ~Messages can change types (e.g., from AIMessageChunk to
AIToolCallsMessageChunk)~
- Output parsers parse additional_kwargs (during .invoke they read off
tool calls).

Packages outside of `partners/`:
- https://github.com/langchain-ai/langchain-cohere/pull/7
- https://github.com/langchain-ai/langchain-google/pull/123/files

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
5 months ago
Erick Friis 00552918ac
groq: xfail tool_choice tests (#20247) 5 months ago
Bagatur f06cb59ab9
groq[patch]: Release 0.1.1 (#20242) 5 months ago
Bagatur 0b2f0307d7
openai[patch]: Release 0.1.2 (#20241) 5 months ago
Bagatur 4b84c9b28c
anthropic[patch]: Release 0.1.7 (#20240) 5 months ago
Bagatur 74d04a4e80
mistralai[patch]: Release 0.1.1 (#20239) 5 months ago
Erick Friis 855ba46f80
standard-tests: a standard unit and integration test set (#20182)
just chat models for now
5 months ago
Erick Friis 9b5cae045c
together: release 0.1.0 (#20225)
Resolved #20217
5 months ago
Eugene Yurtsev 7cfb643a1c
langchain-postgres: Remove remaining README.md file (#20221)
Repository has moved to langchain-ai/langchain-postgres
5 months ago
Eugene Yurtsev 2fa7266ebb
Remove postgres package (#20207)
Package moved
5 months ago
Simon Kelly a682f0d12b
openai[patch]: wrap stream code in context manager blocks (#18013)
**Description:**
Use the `Stream` context managers in `ChatOpenAi` `stream` and `astream`
method.

Using the context manager returned by the OpenAI client makes it
possible to terminate the stream early since the response connection
will be closed when the context manager exists.

**Issue:** #5340
**Twitter handle:** @snopoke

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
5 months ago
kaijietti a812839f0c
community: add request_timeout and max_retries to ChatAnthropic (#19402)
This PR make `request_timeout` and `max_retries` configurable for
ChatAnthropic.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
5 months ago
Erick Friis 391e8f2050
pinecone[patch]: fix core min version (#20177) 5 months ago
Harry Jiang 1ee208541c
langchain: fix pinecone upsert when async_req is set to False (#19793)
Issue: 
When async_req is the default value True, pinecone client return the
multiprocessing AsyncResult object.
When async_req is set to False, pinecone client return the result
directly. `[{'upserted_count': 1}]` . Calling get() method will throw an
error in this case.
5 months ago
Bagatur a27d88f12a
anthropic[patch]: standardize init args (#20161)
Related to #20085
5 months ago
Bagatur 3490d70238
mistralai[patch]: standardize model params (#20163)
Related to #20085
5 months ago
Bagatur 5ae0e687b3
docs: use standard openai params (#20160)
Part of #20085
5 months ago
Eugene Yurtsev 34a24d4df6
postgres[minor]: Add pgvector community as is (#20096)
This moves langchain pgvector community as is

The only modification is support for psycopg3 rather than psycopg2!
5 months ago
Eugene Yurtsev ba9e0d76c1
postgres[minor]: add postgres checkpoint implementation (#20025)
Adds checkpoint implementation using psycopg
5 months ago
Erick Friis 96dc0ea49d
pinecone[patch]: release 0.1.0 (#20109) 5 months ago
Maxime Perrin 5ac0d1f67b
partners[anthropic]: fix anthropic chat model message type lookup keys (#19034)
- **Description:** Fixing message formatting issue in ChatAnthropic
model by adding dictionary keys for `AIMessageChunk `and
`HumanMessageChunk`
  - **Issue:** #19025 
  - **Twitter handle:** @maximeperrin_

Co-authored-by: Maxime Perrin <mperrin@doing.fr>
Co-authored-by: Erick Friis <erick@langchain.dev>
6 months ago
Bagatur 46f580d42d
docs: anthropic tool docstring (#20091) 6 months ago
Erick Friis 28dfde2cb2
cohere: move package to external repo (#20081) 6 months ago
Bagatur 1b7ed6071a
anthropic[patch]: Release 0.1.6 (#20026) 6 months ago
Bagatur 6860450e48
anthropic[patch]: use anthropic 0.23 (#20022) 6 months ago
Bagatur be3dd62de4
anthropic[patch]: fix experimental tests (#20021) 6 months ago
Bagatur 86fdb79454
anthropic[patch]: bump core dep (#20019)
]
6 months ago
Bagatur 209de0a561
anthropic[minor]: tool use (#20016) 6 months ago
harry-cohere e103492eb8
cohere: Add citations to agent, flexibility to tool parsing, fix SDK issue (#19965)
**Description:** Citations are the main addition in this PR. We now emit
them from the multihop agent! Additionally the agent is now more
flexible with observations (`Any` is now accepted), and the Cohere SDK
version is bumped to fix an issue with the most recent version of
pydantic v1 (1.10.15)
6 months ago
Erick Friis 51bdfe04e9
groq: handle streaming tool call case (#19978) 6 months ago
Erick Friis 5acb564d6f
groq: fix core version (#19976) 6 months ago
Erick Friis 9e60159043
groq: release 0.1.0 (#19975) 6 months ago
Graden Rea 88cf8a2905
groq: Add tool calling support (#19971)
**Description:** Add with_structured_output to groq chat models
**Issue:** 
**Dependencies:** N/A
**Twitter handle:** N/A
6 months ago
Eugene Yurtsev d6d843ec24
langchain-postgres: Initial package with postgres chat history implementation (#19884)
- [x] Add in code examples for the chat message history class
- [ ] ~Add docs with notebook examples~ (can this be done later?)
- [x] Update README.md
6 months ago
Erick Friis d5a2ff58e9
pinecone[patch]: source tag (#19739) 6 months ago
harry-cohere beab9adffb
cohere: Improve integration test stability, fix documents bug (#19929)
**Description**: Improves the stability of all Cohere partner package
integration tests. Fixes a bug with document parsing (both dicts and
Documents are handled).
6 months ago
harry-cohere 37fc1c525a
cohere: simplify integration test (#19928)
**Description**: This PR simplifies an integration test within the
Cohere partner package:
 * It no longer relies on exact model answers
 * It no longer relies on a third party tool
6 months ago
billytrend-cohere de6c0cf248
cohere, docs: update imports and installs to langchain_cohere (#19918)
cohere: update imports and installs to langchain_cohere

---------

Co-authored-by: Harry M <127103098+harry-cohere@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
6 months ago
Erick Friis 146d1a6347
cohere[patch]: release 0.1.0rc2 (#19924) 6 months ago
harry-cohere e2b83c87b1
cohere[patch]: Add multihop tool agent (#19919)
**Description**: Adds an agent that uses Cohere with multiple hops and
multiple tools.

This PR is a continuation of
https://github.com/langchain-ai/langchain/pull/19650 - which was
previously approved. Conceptually nothing has changed, but this PR has
extra fixes, documentation and testing.

---------

Co-authored-by: BeatrixCohere <128378696+BeatrixCohere@users.noreply.github.com>
Co-authored-by: Erick Friis <erickfriis@gmail.com>
6 months ago
Massimiliano Pronesti 06dac394a6
cohere[patch]: support request timeout in BaseCohere (#19641)
As in #19346, this PR exposes `request_timeout` in `BaseCohere`, while
`max_retires` is no longer a parameter of the beneath client
(`cohere.Client`) and it is already configured in
`langchain_cohere.llms.Cohere`.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
6 months ago
Erick Friis 0b0a55192f
robocorp[patch]: fix core min version (#19879) 6 months ago
Mikko Korpela 3f06cef60c
robocorp[patch]: Fix nested arguments descriptors and tool names (#19707)
Thank you for contributing to LangChain!

- [x] **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"


- [x] **PR message**:
- **Description:** Fix argument translation from OpenAPI spec to OpenAI
function call (and similar)
- **Issue:** OpenGPTs failures with calling Action Server based actions.
    - **Dependencies:** None
    - **Twitter handle:** mikkorpela


- [x] **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.~


- [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.
6 months ago
Erick Friis 4fbdc2a7ee
openai[patch]: remove openai chunk size validation (#19878) 6 months ago