### What problem does this PR solve?
Both tokenizer (`rag/flow/tokenizer/tokenizer.py`) and
`BuiltinEmbed.encode`
(`rag/llm/embedding_model.py`) currently accumulate embedding batches
via
`np.concatenate` inside the per-batch loop. `np.concatenate` allocates a
new
array and copies all existing data on every call, so accumulating N
batches
is O(N²) in both time and peak memory.
Replacing the incremental concatenate with a list-of-batches + a single
`np.vstack` at the end gives O(N) total work.
For tokenizer the title-vector broadcast `np.concatenate([vts[0]] * N)`
is
also replaced by `np.tile`, which does the same job with a single
contiguous
allocation instead of building a Python list of references.
This is purely a CPU/memory optimisation — output shape and dtype are
unchanged. Measured impact grows with document size:
- 1k chunks (batch 512, 2 iters): ~negligible
- 10k chunks (20 iters): ~10× speedup on this stage
- 100k chunks (195 iters): ~100× speedup, and peak RAM
drops from O(N) extra to near-zero
### Type of change
- [x] Performance Improvement
Co-authored-by: yoan sapienza <Yoan Sapienza yoan.sapienza@orange.fr Yoan Sapienza zappy@macbookpro.home>
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
### What problem does this PR solve?
Adds Perplexity contextualized embeddings API as a new model provider,
as requested in #13610.
- `PerplexityEmbed` provider in `rag/llm/embedding_model.py` supporting
both standard (`/v1/embeddings`) and contextualized
(`/v1/contextualizedembeddings`) endpoints
- All 4 Perplexity embedding models registered in
`conf/llm_factories.json`: `pplx-embed-v1-0.6b`, `pplx-embed-v1-4b`,
`pplx-embed-context-v1-0.6b`, `pplx-embed-context-v1-4b`
- Frontend entries (enum, icon mapping, API key URL) in
`web/src/constants/llm.ts`
- Updated `docs/guides/models/supported_models.mdx`
- 22 unit tests in `test/unit_test/rag/llm/test_perplexity_embed.py`
Perplexity's API returns `base64_int8` encoded embeddings (not
OpenAI-compatible), so this uses a custom `requests`-based
implementation. Contextualized vs standard model is auto-detected from
the model name.
Closes#13610
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
This PR aims to extend the list of possible providers. Adds new Provider
"RAGcon" within the Ollama Modal. It provides all model types except OCR
via Openai-compatible endpoints.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Jakob <16180662+hauberj@users.noreply.github.com>
### What problem does this PR solve?
Refact: switch from oogle-generativeai to google-genai #13132
Refact: commnet out unused pywencai.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Add support `doubao-embedding-vision` model.
`doubao-embedding-large-text` is deprecated.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: bedrock iam authentication #12008
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Only support MinerU-API now, still need to complete frontend for
pipeline to allow the configuration of MinerU options.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Fix: presentation parsing #11920
Fix: Embeddin encode exception handling
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: jina embedding issue #11614
Feat: Add jina embedding v4
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Jason <ggbbddjm@gmail.com>
### What problem does this PR solve?
1. Move EMBEDDING_CFG to common.globals
2. Fix error imports
3. Move signal handles to common/signal_utils.py
### Type of change
- [x] Refactoring
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Introduced gpu profile in .env
Added Dockerfile_tei
fix datrie
Removed LIGHTEN flag
### Type of change
- [x] Documentation Update
- [x] Refactoring
### Related issues
#10078
### What problem does this PR solve?
Integrate DeerAPI provider.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
Co-authored-by: DeerAPI <tensor.null@gmail.com>
### What problem does this PR solve?
Rename the CometEmbed and CometSeq2txt classes to CometAPIEmbed and
CometAPISeq2txt, and correct supported_models.mdx.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Related PR:
Feat: add CometAPI to LLMFactory and update related mappings #10119
Change:
Fixes the issue where the embedding model in CometAPI was not being
called correctly
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: TensorNull <tensor.null@gmail.com>
### Related issues
#10078
### What problem does this PR solve?
Integrate CometAPI provider.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
fix text input exceed token num limit when using siliconflow's embedding
model BAAI/bge-large-zh-v1.5 and BAAI/bge-large-en-v1.5, truncate before
input.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Dataflow supports Spreadsheet and Word processor document
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The default value for OpenAI '/v1/embeddings' parameter
'encoding_format' is 'base64'. Use 'float' explicitly to avoid base64
encoding & decoding, larger data size.
https://github.com/openai/openai-python/blob/main/src/openai/resources/embeddings.py
if not is_given(encoding_format):
params["encoding_format"] = "base64"
### Type of change
- [x] Performance Improvement
Updated constructors for base and derived classes in chat, embedding,
rerank, sequence2txt, and tts models to accept **kwargs. This change
improves extensibility and allows passing additional parameters without
breaking existing interfaces.
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: IT: Sop.Son <sop.son@feavn.local>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
### What problem does this PR solve?
fix error 429 api rate limit when building knowledge graph for all chat
model and Mistral embedding model.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add model provider DeepInfra. This model list comes from our community.
NOTE: most endpoints haven't been tested, but they should work as OpenAI
does.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Based on https://github.com/infiniflow/ragflow/issues/8740
1. A better handle for 'NoneType' object is not subscriptable
2. Add some logs to get the internal message
### Type of change
- [x] Refactoring
fix: retry embedding with Qwen family models when limits temporarily
reached.
APIs of Qwen family models are limited by calling rates. When reached,
the "output" attribute of the "resp" will be None, and in turn cause
TypeError when trying to retrieve "embeddings". Since these limits are
almost temporary, I have added a simple retry mechanism to avoid it.
Besides, if retry_max reached, the error can be early raised, instead of
hidden behind "TypeError".
### What problem does this PR solve?
Sometimes Qwen blocks calling due to rate limits, but it will cause the
whole parsing procedure stops when creating knowledge base. In this
situation, resp["output"] will be None, and resp["output"]["embeddings"]
will cause TypeError. Since the limits are temporary, I apply a simple
retry mechanism to solve it.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
