You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/partners
Jacob Lee 181a61982f
anthropic[minor]: Adds streaming tool call support for Anthropic (#22687)
Preserves string content chunks for non tool call requests for
convenience.

One thing - Anthropic events look like this:

```
RawContentBlockStartEvent(content_block=TextBlock(text='', type='text'), index=0, type='content_block_start')
RawContentBlockDeltaEvent(delta=TextDelta(text='<thinking>\nThe', type='text_delta'), index=0, type='content_block_delta')
RawContentBlockDeltaEvent(delta=TextDelta(text=' provide', type='text_delta'), index=0, type='content_block_delta')
...
RawContentBlockStartEvent(content_block=ToolUseBlock(id='toolu_01GJ6x2ddcMG3psDNNe4eDqb', input={}, name='get_weather', type='tool_use'), index=1, type='content_block_start')
RawContentBlockDeltaEvent(delta=InputJsonDelta(partial_json='', type='input_json_delta'), index=1, type='content_block_delta')
```

Note that `delta` has a `type` field. With this implementation, I'm
dropping it because `merge_list` behavior will concatenate strings.

We currently have `index` as a special field when merging lists, would
it be worth adding `type` too?

If so, what do we set as a context block chunk? `text` vs.
`text_delta`/`tool_use` vs `input_json_delta`?

CC @ccurme @efriis @baskaryan
3 months ago
..
ai21 multiple: implement ls_params (#22621) 4 months ago
airbyte airbyte[patch]: airbyte-cdk compatible pydantic versions (#21738) 4 months ago
anthropic anthropic[minor]: Adds streaming tool call support for Anthropic (#22687) 3 months ago
azure-dynamic-sessions docs: add aca-ds (#21746) 4 months ago
chroma partners: fix numpy dep (#22858) 3 months ago
couchbase couchbase: Add the initial version of Couchbase partner package (#22087) 4 months ago
exa multiple: releases with relaxed core dep (#21724) 4 months ago
fireworks fireworks[patch]: add usage_metadata to (a)invoke and (a)stream (#22906) 3 months ago
groq docs: Standardize ChatGroq (#22751) 3 months ago
huggingface docs: standardize ChatHuggingFace (#22693) 3 months ago
ibm ibm[patch]: release 0.1.7 (#21737) 4 months ago
milvus milvus[patch]: Release 0.1.1 (#22499) 4 months ago
mistralai mistral[patch]: add usage_metadata to (a)invoke and (a)stream (#22781) 3 months ago
mongodb partners: fix numpy dep (#22858) 3 months ago
nomic nomic[patch]: Release 0.1.2 (#22561) 4 months ago
openai partners: fix numpy dep (#22858) 3 months ago
pinecone partners: fix numpy dep (#22858) 3 months ago
prompty docs: fix some spelling mistakes caught by newest version of code spell (#22090) 4 months ago
qdrant qdrant[patch]: Use collection_exists API instead of exceptions (#22764) 3 months ago
robocorp robocorp: typo (#22509) 4 months ago
together together: bump langchain-core (#22616) 4 months ago
upstage together, upstage: bump minimum langchain-openai version (#22505) 4 months ago
voyageai partners: Remove unnecessary print from voyageai embeddings (#21865) 4 months ago