Commit Graph

11 Commits

Author SHA1 Message Date
htaoruan
bcc771e37c
docs: ChatTongyi example error (#19013) 2024-03-17 01:55:56 +00:00
Shuai Liu
c244e1a50b
community[patch]: Fixed bug in merging generation_info during chunk concatenation in Tongyi and ChatTongyi (#19014)
- **Description:** 

In #16218 , during the `GenerationChunk` and `ChatGenerationChunk`
concatenation, the `generation_info` merging changed from simple keys &
values replacement to using the util method
[`merge_dicts`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py):


![image](https://github.com/langchain-ai/langchain/assets/2098020/10f315bf-7fe0-43a7-a0ce-6a3834b99a15)

The `merge_dicts` method could not handle merging values of `int` or
some other types, and would raise a
[`TypeError`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py#L55).

This PR fixes this issue in the **Tongyi and ChatTongyi Model** by
adopting the `generation_info` of the last chunk
and discarding the `generation_info` of the intermediate chunks,
ensuring that `stream` and `astream` function correctly.

- **Issue:**  
    - Related issues or PRs about Tongyi & ChatTongyi: #16605, #17105 
    - Other models or cases: #18441, #17376
- **Dependencies:** No new dependencies
2024-03-15 16:27:53 -07:00
mackong
9678797625
community[patch]: callback before yield for _stream/_astream (#17907)
- Description: callback on_llm_new_token before yield chunk for
_stream/_astream for some chat models, make all chat models in a
consistent behaviour.
- Issue: N/A
- Dependencies: N/A
2024-02-22 16:15:21 -08:00
Bagatur
66e45e8ab7
community[patch]: chat model mypy fixes (#17061)
Related to #17048
2024-02-05 13:42:59 -08:00
Harrison Chase
4eda647fdd
infra: add -p to mkdir in lint steps (#17013)
Previously, if this did not find a mypy cache then it wouldnt run

this makes it always run

adding mypy ignore comments with existing uncaught issues to unblock other prs

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-02-05 11:22:06 -08:00
Funkeke
7220124368
community[patch]: fix tongyi completion and params error (#15544)
fix tongyi completion json parse error and prompt's params error

---------

Co-authored-by: fangkeke <3339698829@qq.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2024-01-15 11:43:13 -08:00
Kai
5d05df4bce
community: Fixed bug of "system message check" in chat_models/tongyi. (#15631)
- **Description:** This PR is to fix a bug of "system message check" in
langchain_community/ chat_models/tongyi.py
- **Issue:** In term of current logic, if there's no system message in
the chat messages, an error of "System message can only be the first
message." will be wrongly raised.
  - **Dependencies:** No.
  - **Twitter handle:** I don't have a Twitter account.
2024-01-07 08:30:18 -08:00
chyroc
37ad6ec248
Refactor: use SecretStr for tongyi chat-model (#15102) 2024-01-02 15:45:23 -08:00
Shuai Liu
4b53440e70
Upgrades the Tongyi LLM and ChatTongyi Model (#14793)
- **Description:** fixes and upgrades for the Tongyi LLM and ChatTongyi
Model
      - Fixed typos; it should be `Tongyi`, not `OpenAI`.
- Fixed a bug in `stream_generate_with_retry`; it's a real stream
generator now.
- Fixed a bug in `validate_environment`; the `dashscope_api_key` should
be properly handled when set by environment variables or initialization
parameters.
- Changed the `dashscope` response to incremental output by setting the
parameter `incremental_output`, which eliminates the need for the
prefix-removal trick.
      - Removed some unused parameters, like `n`, `prefix_messages`.
      - Added `_stream` method.
- Added async methods support, such as `_astream`, `_agenerate`,
`_abatch`.
  - **Dependencies:** No new dependencies.
  - **Tag maintainer:** @hwchase17 

> PS: Some may be confused about the terms `dashscope`, `tongyi`, and
`Qwen`:
> - `dashscope`: A platform to deploy LLMs and provide APIs to invoke
the LLM.
> - `tongyi`: A brand name or overall term about Alibaba Cloud's LLM/AI.
> - `Qwen`: An LLM that is open-sourced and deployed in `dashscope`.
> 
> We use the `dashscope` SDK to interact with the `tongyi`-`Qwen` LLM.

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-12-29 12:06:12 -08:00
Leonid Ganeline
b2fd41331e
docs: docstrings langchain_community update (#14889)
Addded missed docstrings. Fixed inconsistency in docstrings.

**Note** CC @efriis 
There were PR errors on
`langchain_experimental/prompt_injection_identifier/hugging_face_identifier.py`
But, I didn't touch this file in this PR! Can it be some cache problems?
I fixed this error.
2023-12-19 08:58:24 -05:00
Bagatur
ed58eeb9c5
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
Moved the following modules to new package langchain-community in a backwards compatible fashion:

```
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
```

Moved the following to core
```
mv langchain/langchain/utils/json_schema.py core/langchain_core/utils
mv langchain/langchain/utils/html.py core/langchain_core/utils
mv langchain/langchain/utils/strings.py core/langchain_core/utils
cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py
rm langchain/langchain/utils/env.py
```

See .scripts/community_split/script_integrations.sh for all changes
2023-12-11 13:53:30 -08:00