Commit Graph

21 Commits

Author SHA1 Message Date
ccurme
b57aa89f34
multiple: implement ls_params (#22621)
implement ls_params for ai21, fireworks, groq.
2024-06-06 16:51:37 +00:00
ccurme
3999761201
multiple: add stop attribute (#22573) 2024-06-06 12:11:52 -04:00
ccurme
fbfed65fb1
core, partners: add token usage attribute to AIMessage (#21944)
```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."""
    ...
```
2024-05-23 14:21:58 -04:00
ccurme
181dfef118
core, standard tests, partner packages: add test for model params (#21677)
1. Adds `.get_ls_params` to BaseChatModel which returns
```python
class LangSmithParams(TypedDict, total=False):
    ls_provider: str
    ls_model_name: str
    ls_model_type: Literal["chat"]
    ls_temperature: Optional[float]
    ls_max_tokens: Optional[int]
    ls_stop: Optional[List[str]]
```
by default it will only return
```python
{ls_model_type="chat", ls_stop=stop}
```

2. Add these params to inheritable metadata in
`CallbackManager.configure`

3. Implement `.get_ls_params` and populate all params for Anthropic +
all subclasses of BaseChatOpenAI

Sample trace:
https://smith.langchain.com/public/d2962673-4c83-47c7-b51e-61d07aaffb1b/r

**OpenAI**:
<img width="984" alt="Screenshot 2024-05-17 at 10 03 35 AM"
src="https://github.com/langchain-ai/langchain/assets/26529506/2ef41f74-a9df-4e0e-905d-da74fa82a910">

**Anthropic**:
<img width="978" alt="Screenshot 2024-05-17 at 10 06 07 AM"
src="https://github.com/langchain-ai/langchain/assets/26529506/39701c9f-7da5-4f1a-ab14-84e9169d63e7">

**Mistral** (and all others for which params are not yet populated):
<img width="977" alt="Screenshot 2024-05-17 at 10 08 43 AM"
src="https://github.com/langchain-ai/langchain/assets/26529506/37d7d894-fec2-4300-986f-49a5f0191b03">
2024-05-17 13:51:26 -04:00
Erick Friis
bd3e7d50f3
fireworks: bump min core version (#21741) 2024-05-15 19:29:13 -07:00
Erick Friis
aca98fd150
multiple: releases with relaxed core dep (#21724) 2024-05-15 19:29:35 +00:00
Erick Friis
c77d2f2b06
multiple: core 0.2 nonbreaking dep, check_diff community->langchain dep (#21646)
0.2 is not a breaking release for core (but it is for langchain and
community)

To keep the core+langchain+community packages in sync at 0.2, we will
relax deps throughout the ecosystem to tolerate `langchain-core` 0.2
2024-05-13 19:50:36 -07:00
ccurme
9ec7151317
fireworks: fix integration tests (#20973) 2024-04-27 19:49:46 +00:00
Erick Friis
8c95ac3145
docs, multiple: de-beta with_structured_output (#20850) 2024-04-24 19:34:57 +00:00
Erick Friis
e6806a08d4
multiple: standard chat model tests (#20359) 2024-04-11 18:23:13 -07:00
Bagatur
799714c629
release anthropic, fireworks, openai, groq, mistral (#20333) 2024-04-11 09:19:52 -07:00
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>
2024-04-09 18:41:42 -05:00
aditya thomas
16ef88a87d
docs: moving FireworksEmbeddings documentation to docs folder (#19398)
**Description:** Moving FireworksEmbeddings documentation to the
location docs/integration/text_embedding/ from langchain_fireworks/docs/
**Issue:** FireworksEmbeddings documentation was not in the correct
location
**Dependencies:** None

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-22 23:24:22 +00:00
Bagatur
c54d6eb5da
fireworks[patch]: support "any" tool_choice (#18343)
per https://readme.fireworks.ai/docs/function-calling
2024-03-01 11:12:28 -08:00
Yufei (Benny) Chen
2b93206f02
fireworks[patch]: Fix fireworks async stream (#18372)
- **Description:**  Fix the async stream issue with Fireworks
- **Dependencies:** fireworks >= 0.13.0

```
tests/integration_tests/test_chat_models.py ..........                                                                   [ 45%]
tests/integration_tests/test_compile.py .                                                                                [ 50%]
tests/integration_tests/test_embeddings.py ..                                                                            [ 59%]
tests/integration_tests/test_llms.py .........                                                                           [100%]
```
```
tests/unit_tests/test_embeddings.py .                                                                                    [ 16%]
tests/unit_tests/test_imports.py .                                                                                       [ 33%]
tests/unit_tests/test_llms.py ....                                                                                       [100%]
```

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-01 09:20:26 -08:00
Erick Friis
3c8a115e21
fireworks[patch]: remove custom async and stream implementations (#18363) 2024-03-01 03:20:02 +00:00
William FH
f481cbb32d
fireworks[patch]: Fix fireworks bind tools (#18352)
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-01 01:18:15 +00:00
William De Vena
412148773c
Updated partners/fireworks README (#18267)
## PR title
partners: changed the README file for the Fireworks integration in the
libs/partners/fireworks folder

## PR message
Description: Changed the README file of partners/fireworks following the
docs on https://python.langchain.com/docs/integrations/llms/Fireworks

The README includes:

- Brief description
- Installation
- Setting-up instructions (API key, model id, ...)
- Basic usage

Issue: https://github.com/langchain-ai/langchain/issues/17545

Dependencies: None

Twitter handle: None
2024-02-29 14:55:03 -08:00
Bagatur
242af4b5a4
openai[patch], mistral[patch], fireworks[patch]: releases 0.0.8, 0.0.5, 0.0.2 (#18186) 2024-02-27 04:22:24 -08:00
Bagatur
1e8ab83d7b
langchain[patch], core[patch], openai[patch], fireworks[minor]: ChatFireworks.with_structured_output (#18078)
<img width="1192" alt="Screenshot 2024-02-24 at 3 39 39 PM"
src="https://github.com/langchain-ai/langchain/assets/22008038/1cf74774-a23f-4b06-9b9b-85dfa2f75b63">
2024-02-26 12:46:39 -08:00
Yufei (Benny) Chen
ee6a773456
fireworks[patch]: Add Fireworks partner packages (#17694)
---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-23 20:45:47 +00:00